RELEASE NOTES
New features, bug fixes, and content you might've missed.
đ Release Notes: Orbital Drift Suite, Page Fit Enhancements, Ask Integration, Bulk Content Generation & Embedding Upgrades
đ Orbital Drift Suite
The Orbital Drift Suite helps you understand how well your content aligns with your core topicsâand gives you AI-powered tools to realign content at the chunk level.
It includes:
- Orbital Drift Visualizer â diagnose drift across your entire site
- Orbital Drift Stabilizer â fix drift using AI Assist
1) Orbital Drift Visualizer
See which pages reinforce your brandâand which drift away.
The Visualizer measures the semantic distance between each page and your websiteâs core embedding centroid, placing pages into:
- Core
- Focus
- Expansion
- Peripheral
You get a full-site perspective on topic alignment, supported by an interactive radial visualization and page-level insights.
2) Orbital Drift Stabilizer
Fix drift preciselyâone chunk at a time, with AI.
The Stabilizer breaks your content into semantic chunks and helps you realign them using embeddings and AI Assist.
Choose what to realign:
- A webpageâs top embedding cluster
- Custom content you paste
- A specific embedding chunk from any page
Choose your alignment anchor:
- Your websiteâs top embedding cluster centroid
- Any custom anchor you provide
AI Assist will:
- Re-align content toward your chosen anchor
- Improve topical consistency
- Preserve meaning while tightening focus
đĽ How Market Brewâs Drift Workflow Compares to Competitors
⢠Drift Measurement
Competitors: Requires exports + multiple tools
Market Brew: Fully native
Eliminates setup and external dependencies
⢠Core Topic Detection
Competitors: Manually defined
Market Brew: Automatically computed from embeddings
Data-driven brand identity
⢠Visualization
Competitors: Static, limited views
Market Brew: Interactive + chunk-aware
Faster, deeper diagnosis
⢠Insight Quality
Competitors: Manual interpretation
Market Brew: Automated insights
Scales across large sites
⢠Fixing Drift
Competitors: Manual rewriting
Market Brew: AI-powered realignment
Diagnose â fix in minutes
⢠Workflow Integration
Competitors: Fragmented across several tools
Market Brew: Seamless (Visualizer â Stabilizer â Booster)
Complete closed-loop optimization
Market Brew doesnât just show driftâit helps you correct it.
đ§ Website Embedding Listing Enhancements
The Website Embedding Listing now includes:
- Drift scores for every embedding
- Sorting and filtering by drift, similarity, cluster, or URL
- Clicking any drift score opens the Orbital Drift Stabilizer
- A âView Page-Level Driftâ button to open the full Visualizer
This screen now acts as a central hub for diagnosing and correcting semantic drift.
đ Page Fit Scoring Across Ask, AI Overviews Visualizer & AI Overviews Author
Page Fit scoring is now available across both major AI Overview tools, giving you full visibility into how well your content matches user intent.
AI Overviews Visualizer
The Page Fit section shows:
- Minimum, average, and maximum Page Fit
- Detailed Page Fit per page
- Clear explanations of what Page Fit means
- Direct links into the Orbital Drift Stabilizer to improve topical alignment
This helps you understand why certain pages are selectedâor not selectedâin AI Overview results.
AI Overviews Author
The Author tool has been upgraded for a better editing experience:
UX Enhancements
- Cleaner input areas for testing new content
- Improved layout for readability and guidance
- Clearer indicators of how changes affect Page Fit
Page Fit Integration
Just like the Visualizer, the Author now shows Page Fit for the content youâre modifyingâallowing you to test, adjust, and re-score content instantly.
Direct Drift Fixing
Both tools now provide one-click links to open the Orbital Drift Stabilizer with:
- The pageâs top embedding cluster, or
- Specific problematic chunks preloaded and ready to be realigned.
đ¤ Ask Integration: Fix Drift and Page Fit With One Click
Ask now includes:
â Chunk-level links
Link from specific low-scoring embeddings directly to the Orbital Drift Stabilizer.
â Page-level links
Fix overall Page Fit by aligning the top embedding cluster via the Stabilizer.
This creates a full corrective workflow:
Ask â Identify â Drift Stabilizer â Realign â Ask â Re-score
đ Bulk Content Booster Generation
To generate multiple Content Boosters quickly:
How to access
Go to the Content Booster listing screen and click âBulk Create.â
What you can do
- Paste a list of keywords
- Select a Booster configuration
- Optionally specify a target website
- Generate all boosters with one action
A major upgrade for content teams, VARs, and agencies.


















â1. New Pathway for Testing Existing Content (Content Booster â AI Overviews Author)
Many users told us they didnât always want to generate brand-new contentâoften they simply wanted to improve what already exists.
Weâve now added a streamlined pathway that lets content writers:
- Take any existing or recently generated content
- Send it directly into the AI Overviews Author
- Test changes with embeddings
- Compare multiple versions of the content
- Publish updates confidently
This makes Market Brew far more flexible for teams who iterate on existing pages instead of creating from scratch. It also future-proofs workflows now that AI Overviews behavior requires frequent, incremental updates.
Result: Writers can now improve, test, and validate content fasterâwithout being forced into a full Content Booster workflow.
2. Top Tasks Now Reflect âRemaining Workâ After Recrawls
Now that "Top Tasks" is becoming a core navigation system for Market Brew users, we identified a gap:
The Top Tasks list didnât change after work was completed and a recrawl was performed.
Teams needed:
- A clearer sense of which Top Tasks still need attention
- A way to understand progress toward task completion across all Ranking Blueprints
- A more dynamic, real-time prioritization list that updates after every crawl
â Whatâs new
Weâve added a new layer to Top Tasks that surfaces:
- % Completion for each Top Task based on points earned vs. points remaining
- Dynamic reprioritization so Top Tasks reorder based on remaining points, not just total points
- A clearer distinction between:
- Tasks that mattered before work was done
- Tasks that still matter after the most recent recrawl
Why this matters
Users can now:
- See at a glance which tasks are actually worth working on next
- Understand how much impact they've already created
- Avoid clicking into multiple Ranking Blueprints to check progress manually
- Follow an always-up-to-date list of âWhat to do next?â
This effectively turns Top Tasks into a real-time mission scoreboard:
Every time the crawler runs, your task priorities re-rank automatically based on remaining o
Result: Top Tasks becomes an active, living prioritization system, not a static list.
Summary
This release gives users two major upgrades:
â Content teams can now test and refine existing content effortlessly
â SEO teams get a dynamic Top Tasks system that updates automatically after each crawl
Both features push Mission Control closer to becoming a fully automated SEO operations centerâwhere users always know what to do next and have the tools to validate every change.





đ Release Notes: Top Tasks Enhancements â Sorting, Deep Linking, Role Access, and Date Filters
Weâve added another set of improvements to the Top Tasks system to make it even more insightful, actionable, and aligned with how ranking factors shift over time.
These updates extend the diagnostic power of Market Brewâs Ranking Blueprints and Mission Plans, helping you see not just what to fixâbut when Google begins to prefer different ranking factors.
đ§ 1. Sort Tasks by Occurrences or Points
You can now sort the Task Listing by:
- Most Occurrences
- Highest Total Points
- Highest Average Points
This makes it easy to spot the issues that appear most frequently across your templates, as well as those that deliver the greatest ranking impact.
đ 2. Filter Top Tasks by Date Range
Top Tasks now supports date filtering, allowing you to view rankings insights over specific time intervals.
Use this to track:
- How Googleâs weighting of certain ranking factors changes month-to-month
- Which issues increase or decrease in importance over time
- Emerging patterns in Core Web Vitals, page structure, content alignment, and embedding-based scores
- Seasonal or algorithmic shifts in factor preferences
This gives you real visibility into trendline SEOânot just static snapshots.
đ 3. Click Any Task to Dive Straight Into the Optimization List
Every task type is now clickable.
Clicking a task takes you directly to the Optimization Tasks page, automatically filtered to show only that task type across all relevant Ranking Blueprints.
This creates a seamless workflow from discovery â investigation â action.
đ§âđ 4. Expanded Access for Flight Engineer and God Mode
Top Tasks is now fully accessible to:
Flight Engineer
Gives operations teams and agency partners the ability to diagnose patterns across templates and Mission Plans.
God Mode
Full visibility across the entire account, enabling deep audits, template-level pattern detection, and site-wide prioritization.
Together, these enhancements turn Top Tasks into a powerful SEO intelligence systemâone that shows not just where your site stands, but how the search landscape is shifting underneath it.
đ Release Notes: Top Tasks Enhancements
Weâve expanded how Market Brew surfaces high-impact optimization opportunities by introducing Top Tasks at both the Mission Plan level and the Mission Control (account) level. These updates make it dramatically easier to identify structural issues, prioritize work, and understand which SEO tasks will yield the largest improvements across your site.
1. Mission Plan â Top Tasks by Mission Plan
Every Mission Plan now highlights the optimization tasks that appear most frequently across its Ranking Blueprints.
What this reveals
Mission Plans are built from related Ranking Blueprintsâoften representing templates such as all /blog pages or all category pages. When a task appears repeatedly across these Blueprints, it signals a template-level issue. Fixing it once improves many pages at the same time.
Whatâs included
- Total occurrences of each task across all Ranking Blueprints in the Mission Plan
- Total impact points (sum of points across Blueprints)
- Average impact value
- Sorting options by occurrence or total points
Featured Highlights
Each Mission Plan now includes a quick summary showing:
- Top 3 Most Frequent Tasks
- Top 3 Most Impactful Tasks (by total points)
This gives teams a fast, high-level understanding of where to focus firstâbefore drilling into the full task list.
2. Mission Control â Top Tasks Across the Entire Account
Mission Control now displays Top Tasks aggregated across all Mission Plans. This provides an account-wide perspective on the issues that most frequently affect your site.
What this reveals
Seeing task frequency and impact across multiple Mission Plans surfaces site-wide structural issuesâthe most powerful opportunities for improving your entire architecture. These are high-ROI fixes that can elevate dozens or hundreds of pages at once.
Whatâs included
- A unified view of Top Tasks Across All Mission Plans
- Task occurrences across the entire account
- Total impact points aggregated across all Ranking Blueprints
- Instant visibility into the optimization tasks that matter most globally
This makes Mission Control truly act as your central dashboard for prioritizing SEO work efficiently and strategically.
đŻ Why This Matters
These enhancements make it easier than ever to:
- Identify systemic, structural issues
- Prioritize optimizations that improve the most pages
- Understand which tasks deliver the highest overall ranking impact
- Give content teams and developers clear, actionable starting points
- Eliminate guesswork when planning SEO initiatives
Top Tasks helps ensure that your time and effort are always spent on the improvements that drive the largest real-world SEO results.




đ Release Notes â Mission Control Upgrade, Brand Bible Overhaul & Content Booster Enhancements
Weâve shipped a major set of improvements across Mission Control, Brand Bible creation, and the Content Booster workflow. These updates strengthen brand consistency, improve content-to-site integration, and make it easier for users to guide content with intent rather than instructions.
â 1. Brand Bible Has Moved: Now Stage 1 of Mission Control
The Brand Bible has officially moved out of Content Booster and now lives as the first step in Mission Control.
Why it matters:
Every piece of content begins with the voice, positioning, and messaging guidelines that define your brand. Placing the Brand Bible at Stage 1 ensures a unified foundation across your entire content pipelineâSignals â Opportunities â Content.
Users now see the Brand Bible at the start of their workflow, with a direct prompt to define or update it.
â 2. Health Score Updated: Brand Foundation Now Included
The Health Score now reflects whether the site has a default Brand Bible set.
New metric added:
- Brand Bible Setup (20 pts)
Sites missing a Brand Bible are marked accordingly, helping users understand why their Health Score may be low and what is required to improve it.
â 3. New Brand Bible Generator Experience
A complete redesign introduces a robust, flexible, and AI-powered way to build a brand foundation.
Three ways to build a Brand Bible:
đš Option 1: Auto-Generate from PDFs + Website Context
Upload PDF documents or other reference files.
Market Brew analyzes them together with the siteâs content to build a full Brand Bible.
đš Option 2: Auto-Generate via Questionnaire
A guided questionnaire captures:
- voice
- positioning
- audience
- differentiators
- tone
- messaging
âŚand converts this into a coherent, structured Brand Bible JSON.
đš Option 3: Manual Editing
Users can edit or rewrite the JSON directly using the schema editor.
All methods auto-save and can be re-generated at any time.
â 4. Brand Bible Quality Analysis & Scoring
Brand Bibles now receive a real-time evaluation score that includes:
- Brand Identity Richness
- Audience Definition
- Editorial Guidance
- Voice Definition
- Messaging Clarity
- Structural Completeness
A unified Overall Quality Score helps users identify whatâs strong and what needs refinement.
All metrics update live as the JSON changes.
đľ Content Booster Enhancements
â 5. New: âFind Incoming Linksâ Button for Generated Content
Every piece of content you generate now includes a Find Incoming Links button.
Using the siteâs embedding chunks, Market Brew identifies the exact paragraphs and pages where an internal link to the new content should be added.
This ensures:
- stronger internal link flow
- improved topical depth
- better alignment with how search engines evaluate content clusters
This is the most precise internal linking assistant weâve ever shipped.
â 6. âCustom Promptâ is now âFocus Promptâ
We've renamed Custom Prompt â Focus Prompt and improved the guidance.
Why?
Users were adding:
- instructions
- formatting commands
- word counts
- H2 requests
- âwrite 2000 wordsâ style directives
âŚbut the system already handles structure, formatting, and length automatically.
What the Focus Prompt is meant for:
- nuanced content direction
- specific angles
- unique narrative goals
- expert-level orientation
- non-keyword content intents
Example prompts:
- âbest hiking boots for kids (focus on durability)â
- âAI overviews for enterprise SEO teamsâ
- âBeginnerâs guide to keto dietâ
This preserves the systemâs structure while giving users creative control.
â Summary
This release dramatically strengthens the foundation of your content pipeline:
- Brand Bible moved to Mission Control â now Stage 1
- Health Score updated to include Brand Bible setup
- New Brand Bible Generator with PDF mode + Questionnaire mode
- Full Brand Bible quality scoring
- New Find Incoming Links button to map internal links automatically
- Custom Prompt renamed to Focus Prompt with clearer guidance








What's New: Mission Control Tutorial
đ Interactive Tutorial Now Available!
We've heard your feedback that Mission Control can be overwhelming at first. We're excited to introduce a brand new interactive tutorial that walks you through every feature in just 2-3 minutes!
⨠What You'll Learn
Quick 8-Step Walkthrough
- Welcome - Overview of what Mission Control does
- Your Dashboard - Understanding your key metrics at a glance
- Website Selection - How to view and filter your websites
- Health Scores - What the 0-100 score means and how it's calculated
- Signal Sources - Setting up Ask, Listen, and Keyword Fueling
- Finding Opportunities - How the Visibility Launchpad identifies content gaps
- Creating Content - Using Content Booster to generate optimized pages
- Getting Started - Your personalized 5-step action plan
Average completion time: Just 2-3 minutes!
đĽ Video Tutorials Included!
Can't find what you need in the text? We've embedded professional video tutorials right into the walkthrough:
- Ask Tutorial - See how to test visitor queries on your site
- Listen Tutorial - Watch how to monitor Google News for trends
- Content Booster Tutorial - Learn the full content generation workflow
Click "Watch Tutorial" buttons to see these features in action without leaving Mission Control!
đ How to Access the Tutorial
First Time Visitors
When you visit Mission Control for the first time, you'll see a friendly welcome message asking if you'd like to take the tour. Click "Start Tutorial" to begin!
Don't want to see it now? No problem - click "No Thanks" and we won't show it again.
Anytime Access
Look for the blue "Show Tutorial" button floating in the bottom-right corner of Mission Control. Click it anytime you need a refresher!
đĄ Tutorial Features
Easy Navigation
- Next/Previous buttons let you move at your own pace
- Progress bar shows how far along you are
- Skip if you already know something
- Restart anytime you want to review
Smart Design
- Clean, easy-to-read layout
- Helpful tips and highlights
- Visual examples throughout
- Works great on desktop, tablet, and mobile
Your Choice
- Take the full tour or skip ahead
- Watch videos or just read the text
- Restart whenever you need a refresher
- Available in multiple languages (coming soon)
đŻ Why We Built This
We listened to your feedback:
- "There's so much here, where do I start?"
- "I don't understand what these numbers mean"
- "How do I set up Listen?"
- "What's the difference between Ask and Content Booster?"
This tutorial answers all these questions and more in a friendly, guided format.
⥠Quick Tips
For New Users
Start with the full tutorial - it's only 2-3 minutes and will save you hours of trial and error!
For Experienced Users
Skip to the steps you need:
- Jump to Step 4 for signal source setup
- Go to Step 6 for Content Booster details
- Check Step 3 if you're confused about health scores
For Visual Learners
Don't miss the embedded videos! They show real examples of using Ask, Listen, and Content Booster.
đ What Users Are Saying
"Finally! I've been using Mission Control for weeks but never really understood the health score. The tutorial explained it in 30 seconds!" - Beta Tester
"The videos are super helpful - seeing it in action made everything click." - Early Adopter
"I love that I can replay it anytime. Great for training new team members!" - Agency Customer
đą Works Everywhere
The tutorial is fully responsive and works great on:
- đť Desktop computers
- đą Mobile phones
- đ˛ Tablets
- đĽď¸ Any screen size
â Frequently Asked Questions
Q: Do I have to take the tutorial?
A: Nope! It's completely optional. Click "No Thanks" if you prefer to explore on your own.
Q: Can I take it more than once?
A: Absolutely! Use the floating "Show Tutorial" button anytime you need a refresher.
Q: How long does it take?
A: The full walkthrough takes 2-3 minutes. You can skip ahead or take longer if you watch the videos.
Q: What if I close it by accident?
A: Just click the "Show Tutorial" button in the bottom-right corner to start again.
Q: Can I share this with my team?
A: Yes! Every user has access to the tutorial. It's great for onboarding new team members.
Q: Will you add more videos?
A: Yes! We're working on videos for Keyword Fueling, EyesOver, and more features.
đ Special Features
Smart Progress Tracking
The system remembers if you've completed the tutorial, so you won't see the welcome prompt every time you visit.
Video Library
All tutorial videos are also available in our complete YouTube playlist if you want to watch them separately.
Future Updates
We'll keep adding more videos and updating the content as we add new features to Mission Control.
đ Get Started Today!
Ready to become a Mission Control expert?
- Visit Mission Control from your dashboard
- Look for the welcome message (first-time visitors)
- Click "Start Tutorial"
- Follow the 8 easy steps
- Watch videos for features you want to learn more about
Or click the blue "Show Tutorial" button anytime!
Your feedback helps us make Mission Control even better!
đ Additional Resources
- Complete Video Playlist: Watch all tutorials
This update includes fixes to blueprint setup, improvements to prompt handling, smarter defaults across signals, and a major internal redesign to speed up Ask.
đ Fix: Prompts Not Being Added in Visibility Launchpad
A bug was preventing prompts from saving correctly in Visibility Launchpad.
This is now resolved â prompts save reliably on the first attempt.
đ§ą Fix: âForce Target Pageâ in Manual Blueprints
When creating a manual blueprint, choosing âForce Target Pageâ wasnât applying the correct page.
This has been fixed so the selected target page is applied automatically with no extra steps or re-crawls.
⥠Major Speed Upgrade for Ask Ranking Blueprints
Weâve redesigned the internal system powering the Ask Ranking Blueprint (Simulate a ChatGPT search), applying the performance breakthroughs developed for our Deep Crawler engine.
- This results in much faster Ask processing, especially for larger Ranking Blueprints.
- You may see some snippets missing for a few days, while the system is reconfiguring.
đŻ Smarter Defaults for New Signals
The default content gap threshold has been updated from 50% â 35% for:
- Ask
- Listen
- EyesOver
This applies only to newly created signals. Existing configurations are unchanged.
đ Fix: Broken Webpage Embedding Link in Link Flow Finder
A broken link inside the Link Flow Finder feature has been corrected so users can navigate directly to the intended page without errors.
đ Improvement: Faster Loading in Embedding-Related Views
Embedding-related views now load faster and feel more responsive, especially on larger sites.
đ Improvement: Content Booster / Templates / Configurations
- Content Booster Templates have been renamed to Configurations
- The Load / Save Configurations have now been moved to separate parts of the Content Booster Setup Wizard
â New Enhancements Released
đš Visibility Launchpad â Keyword & Prompt Frequency Counter
Weâve added a frequency counter to the Visibility Launchpad to show how often a keyword or generated prompt is identified as a content gap.
- If a keyword already exists in the Launchpad and is selected again, its counter increments.
- Prompts also increment based on semantic closeness (not just exact matches).
Why it matters:
Repeatedly surfaced gaps signal high demand or high impact. Now you can prioritize opportunities with the highest likelihood of ranking performance.
đš Setup Wizard â Ranking Blueprint Progress Protection Warning
When starting a new Ranking Blueprint setup, the Setup Wizard now alerts users if the target site is already involved in another RB setup.
"Warning: starting this Ranking Blueprint will pause all Ranking Blueprints for this site until a new crawl completes."
Why it matters:
Running another RB setup with the same target URL forces a full re-crawl â which pauses all existing Ranking Blueprints that depend on that crawl. This avoids accidental disruption of active blueprint analysis or client deliverables.
đš New Signal Source â EyesOver (Social Media Monitoring Integration)
EyesOver has been added as a new Signal Source within the Configure Signal Sources modal.
- Tracks trending conversations across social platforms.
- Identifies real-time content gaps tied to sentiment and keyword spikes.
- Sends opportunities straight into the Visibility Launchpad and Content Booster.
Users will now see a Request Access button.
Users must have an EyesOver license.
By completing the request form, the EyesOver team will reach out to finalize activation.
Why it matters:
You can now detect emerging topics from social before they hit search, then turn them into content opportunities using Market Brewâs predictive modeling.
đ New Enhancements
Automatic Registration Reminder Email
When a user begins registration but doesnât complete it, Market Brew now sends a one-time reminder email with a return link. This prevents users from getting lost and helps reduce abandoned sign-ups.
AI Mode Visualizer â Faster Workflow
Generating a prompt now automatically recalculates prompt coverage.
No extra clicks. No missed recalculations. Instant visibility.
Keyword Fueler â Opens Launchpad in New Tab
Launching directly into the Visibility Launchpad now opens in a new browser tab, preserving your current work and maintaining context within Keyword Fueler.
Affiliate Link Stays Visible
Affiliate links are now persistent across navigation, ensuring easier access and better tracking for partner referrals.
Fair Crawl Distribution for Multiple Sites
Our deep crawler now includes a fairness algorithm. When multiple sites are being crawled simultaneously, the system prioritizes them evenly, preventing any single site from monopolizing crawl resources.
đ§Š Improvements & Fixes
AI Overviews Author â Tooltip Refinements
Tooltips now behave consistently and stay anchored in the correct location.
Content Booster â Long Prompt Handling
Large prompts are now intelligently truncated in preview areas to maintain clean user interface layouts.
Content Booster â Improved SERP Lookup Reliability
Fixed an issue where very large prompts could generate oversized cache identifiers when retrieving SERP data. Cache names are now safely shortened before storage.
Content Booster â Reignite Button
After content generation is completed, the âRe-igniteâ button is now immediately available without page refresh.
Ranking Influence Slider
Dragging influence sliders now reliably keeps the updated value instead of reverting to the previous position.
Listen â Visibility Launchpad Tagging Correction
Items added from Listen are now categorized correctly without being tagged as âManualâ unless explicitly selected.
â Summary
This update focuses on:
- Smoother onboarding and fewer abandoned registrations
- Faster workflows inside AI Mode Visualizer
- Better Content Booster reliability for large prompts
- More intuitive navigation between key tools
- Fair, efficient crawling across all active sites
Each enhancement reduces friction and gives Market Brew users a more seamless experience across the platform.
đ Ask: AI-Mode / LLM Search Testing â Major Upgrade
đ§ Now Available Inside Your Ranking Blueprints
Ask is no longer just a standalone tool â itâs now embedded directly into your Ranking Blueprints for instant LLM search simulations.
đ Whatâs New
1. Simulate a ChatGPT Search
From any Ranking Blueprint, click: Actions â Simulate a ChatGPT Search
Youâll launch the new Ask Assistant, which analyzes how ChatGPT (and other LLMs) would interpret and cite your siteâs content.
This diagnostic simulation shows:
- Which pages and passages LLMs would select to answer a query
- Why certain sites get chosen over yours
- How your contentâs embeddings align (or donât) with LLM query intent
2. Full Citation Transparency
Every Ask response now reveals exactly why it picked each citation, using our new transparency formula:
Final Score = Chunk Relevance Ă Page Fit
- Chunk Relevance â passage-level match to the user query (cosine similarity)
- Page Fit â how well the entire pageâs centroid aligns with that topic
You can expand each result to inspect how the LLM evaluated every passage â including competing sitesâ best-fit sections.
3. New Content Gap & Auto-Generation Controls
The Ask Assistant now integrates with your Content Gap Threshold, allowing you to:
- Set automatic triggers when AI citation coverage falls below target levels
- Identify which clusters or pages need optimization
- Instantly feed those gaps into your Content Boosters
4. âWhat SEOs Can Do With Thisâ Section
Every result now includes clear, actionable guidance:
- Boost Chunk Relevance â tighten headings, intros, and semantic phrases
- Boost Page Fit â improve overall topical cohesion of templates
- High in both = greater odds of being cited by ChatGPT, Perplexity, or Googleâs AI Mode
đĄ Why It Matters
This release turns Ask into a transparent LLM visibility analyzer.
For the first time, SEOs can run a ChatGPT search simulation within their own search engine model and see what an AI actually âreadsâ â and why.
Itâs how you debug AI rankings before the algorithms do.
âď¸ How to Access
- Open any Ranking Blueprint
- Click Actions â Simulate a ChatGPT Search
- Enter your prompt and explore the full Ask Assistant view â including citation scoring, content gaps, and per-website centroid breakdowns.








đ Content Booster Upgrade: Freeform Content Template Editor
Weâve expanded the Template Configuration section of the Content Booster to give users even more flexibility and creative control.
đ Whatâs New
You can now paste content directly into the new WYSIWYG editor instead of specifying a template URL.
This powerful enhancement lets you use any piece of content â from high-performing blog posts to expert-written outlines â as a live template to guide your 7-Stage Content Booster workflow.
âď¸ Why It Matters
Previously, template inspiration was limited to external URLs. Now, your own writers, strategists, or clients can inject brand-aligned content directly into the process.
This means:
- No dependency on external links or pages
- Full editing control inside the Booster
- The ability to bring expert tone, structure, and style into each content generation sequence
âď¸ How It Works
- Open the Template Configuration section inside the Content Booster.
- Either paste your content into the new Template Content Editor, or continue using the Template URL option.
- Adjust Template Influence to control how strongly your template guides each generation stage.
đĄ Use Case Example
An SEO strategist can now paste a brandâs best-performing article directly into the editor â giving the Booster a precise model for voice, structure, and formatting â without ever leaving the platform.

đ New Feature: Bulk Actions for Flight Engineers
Flight Engineer accounts now have access to powerful bulk actions directly within the Mission Plan and Ranking Blueprint Listing screens.
These new tools streamline workflow by allowing multiple Ranking Blueprints to be managed at once â improving efficiency during calibration, crawling, and task recalculation.
Available Bulk Actions:
- â Re-Calculate Tasks
- âď¸ Calibrate Models
- đ Re-Crawl Target Sites
- đ Re-Crawl All Sites
- ⥠Re-Crawl All Sites & Calibrate Models
- đ§ Toggle Calculate-on-Re-Crawl
Accessing Bulk Actions:
- Navigate to a Crew Account (you must be in crew context).
- Click Actions â View Mission Plans or View Ranking Blueprints.
- Use the Bulk Actions dropdown to perform actions on selected blueprints.



đ New Feature: Searcher Location in Listen
You can now set a Searcher Location per search phrase in the Listen product.
This allows you to simulate searches from specific geographic regions (e.g., Austin, Texas, United States) and see the latest news stories from your local search point â giving you region-specific visibility insights.
Highlights:
- Choose between the default location (Ashburn, Virginia) or a custom location.
- Lookup and select any major city with reach data.
- Location selection persists per keyword or prompt, allowing localized news monitoring.


đ Market Brew Release Notes
1. JSON Editors Added to Content Booster
The Content Booster interface now supports fully interactive JSON Editors, enabling direct inspection and editing of structured brand or content data.
- Provides a tree and code view for better visibility.
- Allows saving, requeuing, and detailed exploration of each stageâs data object.
2. Brand Bible Wizard
Introducing the Brand Bible Wizard, a guided experience that walks users through defining their brandâs:
- Identity and positioning
- Voice, tone, and messaging
- Target audiences and needs
- Offerings and benefits
- Visual identity
- Editorial rules
This wizard automatically constructs a comprehensive Brand Bible, which becomes the default reference for all generated content under that website or crew.
3. Listen: Manual Control for Keyword Auto-Generation
Market Brewâs Listen product now provides fine-grained control over automation:
- Keywords and prompts are only automatically added to the Visibility Launchpad if auto-generation is enabled.
- Otherwise, users can manually choose which opportunities to add, ensuring precise curation.
4. Listen: Visual Keyword Indicators
The Listen interface now shows a clearer keyword status at a glance:
- Displays whether a keyword or prompt is already in the Visibility Launchpad.
- Retains indicators for whether a Content Booster has already been auto-generated.
These updates make it easier to track and manage keyword coverage across the visibility workflow.




đ° Listen: Direct Integration with Visibility Launchpad
- New Feature: You can now jump directly from your Listen keyword and prompt results into the Visibility Launchpad to view real-time gap analysis.
- Auto-Creation: Each new news cycle automatically creates corresponding Visibility Launchpad entries, ensuring that all tracked topics are ready for optimization.
- Quick Boosting: Instantly launch a Content Booster from any Listen result to generate optimized content around the identified opportunity.
- UI Update: A new note was added to inform users that every news cycle feeds new keyword and prompt data into Launchpad for continuous improvement.
đŹ Ask: AI-Mode / LLM Search Testing Update
- New Notice: The Ask tool now includes a clear message explaining that this feature operates on a limited internal dataset.
- Users seeking full-site coverage and an embeddable search widget can now contact their Flight Engineer for a custom AI-Mode deployment.
- This upgrade positions Ask as both a diagnostic tool and a gateway to enterprise-level AI search integrations.
⥠Content Booster: Internal Link Fix
- Bug Fix: Resolved an issue where internal links were missing the first forward slash (
/) after the host. - To apply this fix, simply requeue any Content Booster from Stage 4 â new builds will automatically include corrected link paths.
đ§ Self-Checkout (Light Brew / Full Roast)
- License Management: Self-checkout users can now manage their licenses directly via Crew Settings â Licenses â Package â âManage License.â
- This provides full visibility into your active package, renewal dates, and upgrade options.
đ¨âđ Flight Engineers: Affiliate Link System
- New Affiliate Program: Flight Engineers now have a unique signup link under Crew Settings â Affiliate Links.
- New Light Brew and Full Roast customers who sign up through your link will automatically assign you as their Flight Engineer.
- This enables access to their underlying website data for servicing, and unlocks commission opportunities when you upgrade them into Roastery (Enterprise) accounts.
⨠Summary
These updates strengthen the connection between Signals (Listen & Ask) and Opportunity (Visibility Launchpad), while empowering Content (Booster) and Flight Engineers to deliver measurable SEO impact through automation and smart integrations.







â Fixes
- Stage Validation Improvements
Fixed JSON validation for Stages 0â2 in the Content Booster pipeline.
Invalid or malformed inputs now trigger safe resets and no longer break downstream agents. - Brand Bible Default Validation
Users can now safely define their default Brand Bible. Input is validated to ensure itâs valid JSON â preventing issues caused by pasting HTML or other invalid content that previously disrupted agent workflows.
đ Visibility Launchpad Enhancements
- đ Detected Date
Added a new Detected Date column to both Keyword and Prompt Opportunities tables, allowing filtering and sorting by the time each opportunity was discovered. - đĄ Source Filter
Added a Source filter to trace where each keyword or prompt originated:- Ask â Discovered from user conversations in the Ask module
- Listen â Pulled from Google News mentions and monitored topics
- Keyword Fueling â Derived from PPC research
- Manual â Added directly by users
These additions make it easier to understand when and where opportunities were found â helping you prioritize what to launch next with greater visibility.


đ° Listen: Add Manual Triggering
- You can now manually trigger Listen runs anytime â no need to wait for the next scheduled cycle.
- Each run logs into the News Run History, showing detailed progress on URLs found, crawled, and keyword extraction.
- The new Processing and Completed states make it easy to track whatâs happening in real time.
đ Reverse-Engineered Prompts â Instant Content Generation
- The AI Mode Reverse Engineering panel now supports direct content generation.
- Each discovered prompt now includes an âIgnite Contentâ button, letting you launch a Content Booster instantly from any AI Mode prompt.
- This enables a smooth workflow from prompt discovery â content generation â testing, helping you scale high-impact, AI-optimized content faster than ever.
đ§Š Ranking Blueprint: Clone + Enhance
- A new Clone + Enhance button has been added to Calibrated URLs inside Ranking Blueprints.
- You can now instantly use a competitorâs landing page as your Content Booster template URL, pre-filled with the Ranking Blueprint keyword and your target site.
- In one click, clone, enhance, and launch content thatâs engineered to outperform the competition.



đ Market Brew Relaunch: Introducing Self-Checkout Packages + All-New Site Experience
After years of offering only enterprise-level access, Market Brew is now open to everyone. Weâre excited to announce our brand-new self-checkout packages, designed for startups, agencies, and teams ready to bring predictive SEO into their daily workflow.
đ Whatâs New
1. Self-Checkout Packages
For the first time, you can sign up instantly â no sales calls, no setup delays.
Choose your perfect âroastâ:
- â Light Brew â AI Mode Content Booster for startups and small teams
- đĽ Full Roast â Scalable production and advanced automation for growing agencies
- đ The Roastery â Full enterprise access powered by the Chameleon Search Engine
Each plan is built from the same predictive search technology trusted by global brands, now with flexible pricing starting at $249/month.
2. A Completely Refreshed Website
Market Brewâs new design brings a modern, cinematic feel to the brand â blending our space + coffee theme with clean typography, adaptive layouts, and bold color gradients.
Itâs not just a facelift â the entire experience has been re-engineered for clarity, transparency, and instant access.
3. Updated Feature Comparison
Our new feature table makes it easy to see whatâs included at each tier â from the Ask and Listen modules in Light Brew to API Access, SEO Forecasting, and Ranking Blueprints in The Roastery.
đĄ Why It Matters
Predictive SEO shouldnât be locked behind enterprise gates.
Market Brewâs self-service launch empowers every team â from lean startups to global agencies â to test, optimize, and forecast their organic growth using the same algorithms that drive modern search engines.
Visit the new site â marketbrew.ai
Explore the packages, compare features, and start your journey toward predictive SEO mastery.


đ Whatâs New: Smarter Insights, Smarter Healing
Market Brewâs Self-Healing Website system just got a major upgrade. Your AI-driven content engine can now detect, analyze, and fill gaps faster than ever â with full transparency into how each piece of content is discovered, evaluated, and generated.
đ§ ASK: Transparent Discovery Metrics
The Ask Search Assistant now includes visibility metrics that reveal exactly how your content is found when users search for information on your site.
Youâll see how your top pages and sections align with user prompts â a sneak peek into how Googleâs AI Mode works behind the scenes.
Track:
- Best Page Fit (embedding match of your strongest page)
- Best Section Match (embedding match at the content chunk level)
- Content Gap % (the measurable distance between your site and ideal coverage)
These insights now make Ask your real-time content relevance radar.
âď¸ CONFIGURABLE CONTENT GAP THRESHOLDS
When Ask or Listen detects a gap â where your top embedding cluster similarity falls below your defined threshold â the system automatically flags that query as a high-opportunity prompt.
Your Visibility Launchpad will now automatically capture those user prompts for optimization workflows.
Optionally, you can enable Auto-Generation, allowing Market Brew to instantly create a Content Booster for each qualifying gap.
Tune your gap sensitivity, set thresholds, and decide how aggressive your self-healing automation should be.
đ LISTEN: Smarter Extraction with Prompts
Listenâs content intelligence engine now extracts not just keywords, but also prompts â representing the actual questions and topics emerging in your niche.
This upgrade makes Listen a direct feeder into your Visibility Launchpad, helping you detect early content opportunities from news, blogs, and trend sources.
Keywords show whatâs popular.
Prompts show why it matters.
đĄ CONTENT BOOSTERS: Now Powered by Prompts
Content Boosters can now be launched using custom prompts as an alternative to traditional keywords.
That means you can go beyond keyword-focused SEO to generate content around real user intent, just like the systems powering AI search engines.
Whether youâre fixing a content gap, reigniting existing content, or launching something new â your content generation can now be guided by either:
- Target Keyword (traditional SEO optimization)
- Custom Prompt (AI-mode, semantic optimization)
Prompts are how modern search engines think.
Now your content creation can, too.
đ The Self-Healing Website: Fully Connected
Together, these updates bring every module closer into sync:
- Ask detects content gaps from real user behavior.
- Listen surfaces emerging topics and prompt patterns.
- Visibility Launchpad ranks and prioritizes opportunities.
- Content Booster creates new or improved content automatically.
The result: a site that constantly measures, learns, and heals itself â powered by embeddings, not guesswork.
Would you like me to produce a version styled for your in-app âWhatâs Newâ modal (shorter, punchier text with headings + emojis, like the Listen release you used last week)?
Or should this stay in the long-form release note format (for the public changelog / email newsletter)?
â









đ Introducing the Self-Healing Website
Websites have always been reactive.
They wait for updates. They fall behind trends. They leave gaps in what users are asking for.
That ends today.
đ Market Brew is proud to launch the worldâs first Self-Healing Website â a site that:
- Listens to your users (via Ask) and never leaves a query unanswered.
- Scans the market (via Listen) and captures trending topics before competitors.
- Lets you take control (via Keyword Fueling) when strategy demands it.
- Prioritizes opportunities in the Visibility Launchpad with real-time data.
- Auto-generates optimized content using Content Templates + Content Booster.
The result?
đ A living website that detects gaps and heals itself automatically.
No more chasing SEO. No more missed opportunities.
Your website is now a growth engine that adapts in real time.
đ Release Notes: Introducing the Self-Healing Website
A Website That Adapts Itself
Websites have always been reactive â updated manually, chasing after traffic, and falling behind demand. Market Brew changes that with the launch of the Self-Healing Website, a living system that automatically detects and heals content gaps.
With the Self-Healing Website, your site is never static. It constantly listens to your users and the market, identifies gaps in your content, and generates optimized pages automatically.
How It Works: The Healing Loop
The Self-Healing Website is powered by signals, opportunities, templates, and boosters â all connected through the Healing Station.
1. Signal Sources: Demand Detection
Choose from three signal engines to power your websiteâs intelligence:
- Ask (Internal Engine): Captures visitor queries and searches, checks your site embeddings, and answers if possible. If not, it triggers a Content Booster.
- Listen (External Engine): Monitors Google News, crawls top stories, and extracts the keywords driving visibility. Feeds them into Visibility Launchpad for analysis.
- Keyword Fueling (Manual Control): Gives you direct control to inject strategic or evergreen keywords into the pipeline.
All signals flow into Visibility Launchpad.
2. Visibility Launchpad: Opportunity Prioritization
The Visibility Launchpad compares all signals against your site and identifies content gaps.
- Every keyword opportunity is scored by Launch Priority.
- Metrics like Content Gap %, Closest Match, Search Volume, CPC, and Estimated Value help you pick the highest-impact opportunities.
- Market Impact ratings show the overall growth potential.
This is where raw signals become clear, prioritized opportunities for growth.
3. Content Templates: Consistency at Scale
When gaps trigger new content, templates ensure itâs generated your way.
- Save your preferred tone, structure, target word count, linking strategy, and style as templates.
- Reuse templates across Ask, Listen, and Keyword Fueling auto-generation.
- Every piece of content stays on-brand and optimized, no matter how itâs created.
With templates, your website heals itself â but always in your voice.
4. Content Booster: Automated Healing
Finally, Content Booster generates the optimized content.
- Powered by your chosen template.
- Instantly creates pages tuned to fill the exact content gap.
- Publishes fresh, relevant, and SEO-aligned content at scale.
The loop closes â your site is healed.
Healing Station Dashboard
From the Healing Station, you can monitor the full cycle:
- Signals (Ask, Listen, Keyword Fueling) feeding the pipeline.
- Opportunities prioritized in the Visibility Launchpad.
- Content Generated via templates in the Content Booster.
Your siteâs self-healing activity is fully transparent: signals detected, opportunities scored, and new content created.
Why It Matters
- Ask ensures no visitor query goes unanswered.
- Listen ensures no trend goes uncaptured.
- Keyword Fueling ensures you stay in control.
- Visibility Launchpad ensures every gap is prioritized.
- Content Templates ensure consistency across all auto-generated content.
- Content Booster ensures your site heals itself automatically.
Your website becomes a living, self-healing system that constantly adapts to user intent and market demand.
Availability
The Self-Healing Website is now live across Market Brew.
- Configure your signals in Healing Station.
- Monitor opportunities in Visibility Launchpad.
- Power auto-generation with Content Templates.
- Let Content Booster generate optimized pages automatically.
đ Activate your signals and templates today and join the first generation of websites that donât just exist â they heal themselves.






đ Whatâs New: Smart Brand Bible Management
Your Brand, Instantly Understood
Every website tells a story about your brand. Now Content Booster reads that storyâautomaticallyâand turns it into guidance for every piece of content you create.
đ How Brand Bibles Work
Automatic generation (default):
Content Booster builds your brand bible by analyzing:
- Top-performing website pages
- Visual design elements and CSS styling
- Content patterns and on-site messaging
Optional enrichment:
Upload your own materialsâbrand guidelines, style guides, marketing docsâand theyâll be seamlessly folded into the automatically generated brand bible.
The more source material, the stronger and more accurate the brand alignment.
âď¸ Brand Bible Defaults
Save time by setting defaults once and reusing them everywhere:
- Crew Default â A universal standard for your entire team.
- Website Default â Override at the domain level (perfect for agencies or multi-brand companies).
Hierarchy of use:
- Website Default (if set)
- Crew Default (if set)
- Auto-generated (website + uploaded files)
đĽď¸ One Interface, Complete Control
The new Branding section gives you:
- Active Brand Bible â See exactly which brand bible is in play.
- Manage Brand Materials â Upload or replace optional documents.
- Crew Default â View, edit, or set your teamâs baseline bible.
- Website Default â Create overrides for specific domains.
You can even edit the JSON directly with a guided template to accelerate custom setups.
đ Brand Bible Quality Analysis
Every brand bible is scored across 7 dimensions:
- Structural Completeness
- Brand Identity Richness
- Voice Definition
- Messaging Clarity
- Audience Definition
- Editorial Guidance
- Overall Quality
Each score comes with specific metrics and recommendations, e.g.:
- âVoice well-defined with 3 attributesâ
- âMissing: audience demographics and pain pointsâ
- âAdd 2â3 messaging pillars for stronger consistencyâ
đĄ Why It Matters
Old way: Manually configure brand rules for every content project.
New way: Brand identity is automatically understood.
- ⥠Instant analysis of your website
- âą 70â90% faster content generation setup
- đŻ Consistent voice across unlimited content pieces
đŚ Getting Started
- Select your website in Content Booster.
- Your brand bible auto-generates.
- (Optional) Upload additional docs in Manage Brand Materials.
- (Optional) Save as Crew or Website Default.
- Create content with built-in brand alignment.
For agencies: Use a Crew Default for agency voice, plus Website Defaults for each client.
For multi-brand companies: Keep a Crew Default for corporate voice, then layer Website Defaults per brand.
What This Means for You
- Zero Configuration â Brand rules generated from your existing site.
- Consistency â Voice and messaging aligned across all content.
- Flexibility â Upload extra docs or edit JSON as needed.
- Transparency â Quality scores show whatâs strong and whatâs missing.
- Efficiency â Set once, reuse everywhere.
⨠Available now: The new Branding interface is live in Content Booster.



đŚ Release Notes: Content Booster â Stage 6: Quality & Compliance
Weâre excited to introduce Stage 6: Quality & Compliance, a new checkpoint in the Content Booster pipeline designed to ensure every piece of content is not only optimized for SEO but also reader-friendly, trustworthy, and professional.
This stage automatically checks for common pitfalls in AI-generated writing, flags weak or confusing sections, and enforces clear editorial standards.
đ What Stage 6 Does
1. Detects Overused âAI Giveawayâ Words & Phrases
Stage 6 scans for repetitive, low-trust buzzwords like âgame-changerâ or âfuture-proofâ and recommends clear alternatives. Writers are encouraged to:
- Use plain language.
- Add specifics (data, names, anecdotes).
- Write conversationally.
2. Enforces Editorial Clean-Up
- Removes redundant first-sentence padding.
- Flags awkward phrasing (e.g., âdelveâ â suggest âexploreâ or âdive intoâ).
- Replaces em-dashes with more natural punctuation.
- Strips âIn Conclusionâ / âIn Summaryâ headers.
3. Prevents False Confidence & Hallucinations
- Detects fabricated case studies or statistics.
- Blocks unverifiable client names.
- Reinforces compliance with factual accuracy standards.
đ New Stage 6 Metrics in Final Draft Editor
The Final Draft Quality Report now includes a Content Quality score that factors in Stage 6 compliance.
Key checks now visible in the UI:
- Buzzword Detection: Shows total flagged buzzword instances and highlights them inline.
- Structure Score: Evaluates if the intro, body, and conclusion follow natural flow without repetition.
- Weak Language Detection: Flags redundant or vague sentences (esp. intros).
- Overall Quality: Now reflects Stage 6 compliance in its weighted calculation.
For example, in the report above:
- SEO Completeness, Technical Quality, and Accessibility scored 100%.
- Content Quality was pulled down to 75% due to 13 buzzword instances and flagged structural issues.
This helps teams instantly see when content qualityânot just SEO or technical complianceâneeds improvement.
đ Feature Reports Addressed
- Improve Internal Linking Decisions
Internal link relevance now weighs meta titles & descriptions more heavily. Similarity thresholds are stricter to prevent confusing link placements.
đ Bug Fixes
- Target Keyword Self-Cannibalization
Pages optimized for a target keyword (e.g., âbest running shoesâ) no longer link that exact phrase to other internal pages. - Weak / Odd Language in Introductions
Repetitive or unnecessary opening sentences are now flagged, improving first impressions.
â Why It Matters
Stage 6 brings editorial intelligence into Content Booster:
- Keeps language natural and specific.
- Strengthens page focus with smarter internal linking.
- Helps teams publish content that earns trust and ranks well.
With this release, the Final Draft Editor now gives writers not just SEO and technical compliance checksâbut also quality assurance insights that elevate the human readability of every article.

đ Release Notes: Content Booster Upgrades
Weâve rolled out major improvements to Content Booster, making your content generation process smoother, smarter, and more aligned with SEO best practices.
đ Whatâs New
đ§ Five-Step Wizard for Content Setup
The Content Setup process is now a streamlined 5-step wizard, guiding you through everything from keyword targeting to generation settings. Each step is clear, structured, and designed to help you move from idea â optimized draft with confidence.
đ Reverse Engineer Fan-Out Prompts
The old âUse Competitorsâ option is now more powerful â and renamed to Reverse Engineer Fan-Out Prompts.
- Competitor content is analyzed using embeddings.
- Additional fan-out prompts are automatically generated.
- This ensures your content is optimized for all relevant variations search engines associate with your topic.
- â Powered by the same technology as our AI Mode Visualizer, bringing consistency across your optimization toolkit.
đźď¸ Template Configuration (NEW)
You can now use a Template URL to guide structure and style.
- Optional: Leave blank to generate original content, or add a URL from a high-performing page.
- Template Influence Slider: Fine-tune inspiration â from low influence (light reference) to high influence (closely follow template).
- The balance of originality and inspiration is now fully in your control.
đ§Š Friends & Foes Control Quotes
Quotes ( â â ) are now driven entirely by your Friends list.
- If a domain is listed as a Friend, quotes will be included â up to the maximum external links on a page.
- If not, no quotes are added â keeping your output clean and under your control.
đ Smarter External Links
External links are now prioritized based on your Template URL and Friends list:
- Links from your template page are used first.
- If none exist, links are pulled from the SERP.
- Foe URLs are excluded at every step.
This ensures outbound linking aligns with your strategy while avoiding competitors or undesirable domains.
đŽ Coming Soon: Stage 6 Quality & Compliance
Next up, weâre enhancing Content Booster with a Quality and Compliance stage.
- Add guardrails to prevent unwanted sayings, styles, or tone.
- Enforce brand standards and ensure compliance across all generated content.
- Keep every draft consistent with your organizationâs voice and guidelines.
â Summary
With these upgrades, Content Booster now offers:
- A guided 5-step workflow.
- Advanced fan-out prompt generation (using the same tech as our AI Mode Visualizer).
- Flexible template-driven inspiration.
- Cleaner, Friends-first quoting system (up to your pageâs link limit).
- Smarter, context-aware external linking.
- đŽ And soon, Stage 6 Quality & Compliance guardrails.
Content creation just got faster, more controlled, and more SEO-friendly.



đ Release Notes: Ask â AI Search Assistant
Weâre excited to introduce Ask â Your AI Search Assistant, the newest addition to Market Brewâs suite of search-driven tools.
Ask transforms your website into an interactive, intelligent assistant where visitors can ask natural language questions and be guided to the most relevant, trustworthy pages on your site.
Ask works hand-in-hand with Content Boosterâour AI-powered content conveyor belt. With Content Booster, you can scale high-quality commentary and articles; with Ask, you can put that content to work in real time, helping visitors explore and engage with your site.
đ Key Features
- Conversational Search: Users can ask questions like they would in Google or ChatGPTâand get precise, context-aware answers.
- Grounded in Your Corpus: Ask draws only from your websiteâs vetted content, guaranteeing alignment and doctrinal safety.
- Guided Navigation: Every answer links users to the exact page (e.g., commentary, article, or guide) so they can âread more.â
- Ranking-Aware Intelligence: Built on Market Brewâs search engine models, Ask highlights the same factors real search engines use for relevance.
- Persistent Context: Ask remembers chat history for more natural, ongoing conversations.
đ Content Booster + Ask = Complete Loop
- Content Booster (Generative): Creates commentary and articles with guardrails, embedding checks, and stage-by-stage optimization.
- Ask (Agentic): Deploys that content to users in conversational form, with guidance to the right page.
Together, they form a closed-loop ecosystem:
- Content Booster â produces SEO-ready, brand-aligned content.
- Ask â delivers that content back to your audience interactively.
đŽ Coming Soon
For Full Roast subscribers:
- Site Deployment: Add Ask as a widget or connect via API to embed interactive search directly on your website.
- Custom Styling: Match the look and feel of your brand for a seamless user experience.
- Advanced Analytics: Track queries, user engagement, and uncover new content opportunities from real visitor questions.
- Personalized Assistants: Extend Ask into branded clones (e.g., âAsk Jesus,â âAsk Timâ) using Stage 0 Brand Bible + embeddings from Content Booster.
đ Why This Matters
Ask + Content Booster bring both sides of AI to your site:
- Generative AI (Content Booster): Scale scripture-grounded commentary and articles with measurable quality guardrails.
- Agentic AI (Ask): Turn that content into an interactive assistant that answers real visitor questions.
Itâs like having a content factory and a tour guide working togetherâone creates the content, the other delivers it in the most engaging way possible.
⥠Ask is available now inside Market Brew dashboards.
đ Widget + API rollout coming soon for Full Roast customers.



đ Market Brew Unveils Its Most Ambitious UI Overhaul Yet
A bold new era of predictive SEO has arrived.
Market Brew has officially launched a massive redesign of its platform â the most significant visual and usability upgrade in our history. This is more than a facelift. Itâs a complete reimagining of how SEO professionals interact with the worldâs most advanced predictive search engine models.
đ The Future of SEO, Reimagined
The new Market Brew UI is built to inspire. Every detail has been meticulously crafted to reflect who we are: innovative, precise, and approachable.
- A Striking New Look â Powered by deep, confident tones and vibrant accents, the interface feels modern, energetic, and unmistakably Market Brew.
- Typography That Commands Attention â Bold headlines cut through the noise, while clean body text ensures effortless readability across screens.
- A Refined Identity â Our iconic cup has evolved into a sharper, more future-forward symbol, now integrated seamlessly across the platform.
⥠Built for Speed, Designed for Clarity
The redesigned UI isnât just beautiful â itâs powerful.
- Streamlined Navigation means you get where you need to go faster.
- Unified Components create consistency across every workflow.
- Data-First Layouts keep insights front and center, turning complexity into clarity.
⨠An Experience That Feels Alive
With softer edges, fluid lines, and dynamic graphics, the platform feels more human â yet unmistakably high-tech. Subtle animations and expressive visuals bring the invisible mechanics of SEO into focus like never before.
đ Why It Matters
This release marks a new chapter for Market Brew. Our platform has always been about making SEO transparent and predictable. Now, the interface itself matches that promise â clean, modern, and future-focused.
đ Whatâs Next
This is just the beginning. The new UI lays the foundation for upcoming innovations that will push the boundaries of predictive SEO even further. Market Brew is not just keeping up with the future â weâre building it.
Welcome to the new Market Brew.





đ Release Notes â More control, faster decisions, cleaner flow
Keyword Fueling
- Smarter keyword workflow
Related Keywords now appear directly beneath your Hero Keyword in Step 2. Discovery â selection happens in one place, so you can add only the terms that matter.
Visibility Launchpad
- NEW: One-click âFixâ (guided optimization)
Every opportunity now has a Fix button that opens a guided âChoose Your Optimization Approachâ panel with instant context:- Keyword Opportunity details: keyword, Content Gap %, and your Closest Match page.
- Two clear paths:
- YES â Create Ranking Blueprint with Target (use the matched page).
- NO â Create New Content or Create Blueprint without Target (when a different page is the better play).
Why it matters: less guesswork, faster routing, and a consistent way to act on every opportunity.
- Youâre in control (no auto-populate)
We removed the old custom/hide options because the Launchpad no longer auto-adds keywords. You explicitly add them from Keyword Fuelingâwhich means a cleaner list and tighter intent. - Clutter-free rows
Each row now includes a single Delete action. Manage the plan without UI noise.
Content Booster
- Dedicated Link Configuration tab
Link Density and Internal:External settings live in their own tab for quick tuning and less cognitive load. - Streamlined Content Strategy
The Website field now sits directly under Target Keyword for a left-to-right, top-to-bottom setup that just makes sense. - See progress at a glance
The Status column on the Content Booster Listing shows where each piece is in the pipeline (Created, Pending, Processing, Completed, Error, Cancelled, Paused, Archived). - Save without scrolling
The Save button moved to the top of the Final Draft section so you can lock changes the moment theyâre ready.





đ Release Notes: Friend/Foe Domains & Top Organic Results in Content Booster
Overview
Weâve expanded Content Booster with two powerful upgrades: Friend/Foe Domains and Top Organic Results. Together, these features give you unmatched control over both the sources that inspire your content and the external sites your content promotesâensuring every step of the workflow aligns with your strategy.
đ Whatâs New
Friend Domains (đ)
- Mark partner sites or trusted references as Friends.
- Prioritized for external citations (Stage 5).
- Amplifies partnerships and reinforces aligned voices.
Foe Domains (đ)
- Flag competitor sites as Foes.
- Excluded from external linking, even when they rank highly.
- Lets you learn from competitors without sending them authority.
Defaults Management
- Crew Defaults â Apply Friend/Foe rules across all Content Boosters for your team.
- Website Defaults â Apply Friend/Foe rules to every Content Booster tied to a target site.
- Flexible overrides remain available at the individual Booster level.
Top Organic Results (đ)
- Accessed by clicking the information icon next to âUse Competitorsâ or the buttons inside the Friend/Foe tab.
- Instantly shows the current top-ranking organic results for your target keyword.
- Reveals exactly which competitor pages Content Booster will analyze by default when âUse Competitorsâ is enabled and no Friend/Foe list is defined.
- Helps you understand the baseline content inputs driving prompt generation and citations.
Smart Fallbacks
- When neither Friend nor Foe is defined, Content Booster automatically uses the highest-authority organic results for quotes and linkingâensuring credibility and relevance.
â Why It Matters
- Shape the Narrative â Direct inspiration and citations toward allies, not rivals.
- Gain Full Transparency â See the exact organic pages powering your strategy when competitors are in play.
- Stay Consistent at Scale â Crew and Website Defaults keep your whole team aligned.
- Protect Your Edge â Exclude competitors from quotes and links while still learning from their strategies.
- Boost Brand Authority â Elevate trusted, high-quality partners in every piece of content.
This release gives you the clarity, control, and competitive edge you need to confidently guide both the inputs that shape your content and the outputs that elevate your brand.



đ Release Notes: Keyword Fueling Upgrade â Related Keywords
Overview
Weâve upgraded Keyword Fueling with a brand-new Related Keywords experience, giving you richer and more relevant insights for building your visibility strategy. This enhancement ensures your campaigns start with keywords that are directly tied to your hero keyword, eliminating irrelevant noise and aligning the process with your actual intent.
đ Whatâs New
Related Keywords List (â¨)
- Instantly see a comprehensive list of keywords directly related to your hero keyword.
- Each keyword is displayed with search volume, average CPC, and estimated monthly spend to help you prioritize the highest-value opportunities.
- Add keywords to your Keyword Cart with a single click and move them straight into the Visibility Launchpad.
Smarter Starting Point
- Previously, Keyword Fueling only showed top competitor sites and their top keywords.
- Now, the Related Keywords list fixes the âthese keywords have nothing to do with my hero keywordâ issue by ensuring relevance right from the start.
- Competitor keywords are still availableâbut theyâre now enhanced by a foundation of keyword ideas directly aligned with your hero term.
â Why It Matters
- Relevance First â Ensure every suggested keyword actually ties back to your chosen hero keyword.
- Faster Workflow â Skip irrelevant terms and build campaigns with confidence from the start.
- Actionable Insights â With CPC and spend data included, you can instantly gauge keyword value.
- Seamless Strategy â Add keywords directly into the Keyword Cart and launch into the Visibility Launchpad without breaking flow.
This upgrade makes Keyword Fueling more intuitive, more actionable, and laser-focused on your hero keywordâs ecosystemâso you can spend less time filtering noise and more time fueling growth.

đ Release Notes: Use Competitors in Generation Options
Overview
Weâre excited to introduce a powerful new feature in Generation Options: Use Competitors. This setting enables Market Brew to analyze top-performing competitor pages in the SERP for your target keywords and generate content prompts that align with â and surpass â whatâs already ranking.
How It Works
When enabled, Market Brew will:
- Crawl Competitor Pages: Collect and analyze the top landing pages in the search results for your selected keyword.
- Extract Embedding Clusters: Identify the most important content clusters on competitor pages for deeper semantic analysis.
- Generate Enhanced Prompts: Create additional prompts for quotes, external linking, and authority building using competitor insights.
- Fan-Out Prompt Reverse Engineering (if enabled): Derive competitor-based fan-out prompts, uncovering related angles and subtopics your competitors are using.
Benefits
- Competitive Edge: Leverage competitor content strategies to ensure your content is positioned to outperform.
- Rich Prompt Generation: Access more diverse, high-value prompts that reflect what works in the real SERPs.
- Data-Driven Strategy: Reverse-engineer high-ranking competitors to sharpen your own content roadmap.


đ Release Notes: Content Booster Metrics System
Weâve taken Content Booster to the next level by introducing a comprehensive metrics and scoring system. This upgrade transforms Content Booster from a workflow orchestrator into a measurable optimization engine, giving SEOs clear performance insights at every stage of the content lifecycle.
The new metrics framework provides stage-by-stage reporting with detailed performance analysis, enabling teams to spot strengths, diagnose weaknesses, and continuously refine content before deployment.
Whatâs New
đ Stage-Based Metrics
Each stage of Content Booster now generates a Metrics Report with:
- Overall Score â a quick performance snapshot.
- Sub-Metrics â granular KPIs unique to each stage.
- Supporting Data â transparent data points backing every score.
đ Stage Highlights
- Stage 0: Brand Bible Generation
- Scores for Voice Definition, File Quantity, Structure Completeness, Audience Coverage.
- Identifies gaps in tone-of-voice attributes or file diversity.
- Stage 1: Content Opportunity & Strategy
- 100% visibility into objectives, fan-out diversity, schema coverage, FAQ readiness.
- Ensures a solid strategic foundation before writing begins.
- Stage 2: Brief & Structure Generation
- Measures Content Depth, Structure Guidance, Title Variety, Section Accuracy, Schema Completeness, FAQ Integration.
- Guarantees briefs are both structurally sound and SEO-ready.
- Stage 3: Draft Generation
- Evaluates HTML structure, section success, SEO completeness, content diversity, and word count accuracy.
- Helps refine drafts to balance readability and algorithmic alignment.
- Stage 4: Optimization & Alignment
- Scores Semantic Alignment, Content Quality, Structure Preservation.
- Pinpoints sections needing re-optimization for maximum similarity and clarity.
- Stage 5: Internal Linking & Entity Enrichment
- Analyzes Link Density, Link Ratio, Schema Implementation, Link Generation Efficiency.
- Ensures internal links and entities are strategically distributed for ranking impact.
- Stage 6: Quality & Compliance (coming soon)
- Final verification of grammar, plagiarism, accessibility, and brand voice compliance.
Key Benefits
â
Quantifiable Optimization â Clear KPIs at every stage, removing guesswork.
â
Closed-Loop Feedback â See where content underperforms and requeue stages for improvement.
â
Enterprise-Grade Transparency â Supporting data included for every score.
â
Predictive by Design â Aligned with Market Brewâs search engine models to forecast impact.
Availability
The new metrics system is live now in all new Content Boosters.






đ Whatâs New
Keyword Fueling
The Keyword Fueling is now live, completing the Market Brew workflow.
- Select a Target Site â Pick the website you want to optimize.
- Enter Your Hero Keyword â Define the core phrase for your campaign.
- Identify Your Competitors â Pull in competitor sites and capture their entire keyword universe.
- Build Your Keyword Cart â Add the keywords you want to pursue, preparing your mission fuel.
Your cart isnât just a list of terms â itâs the rocket fuel for your Visibility Launchpad. Get ready to suit up.
đ The New Market Brew Workflow Is Now Complete
With this release, the full Market Brew journey is live end-to-end:
- Keyword Fueling â Fill your cart with keywords and competitors.
- Visibility Launchpad â Where keywords meet your content. Your Targeting Console prioritizes launch opportunities so you can identify your Launch Priority and go for launch.
- Content Booster â Ready for ignition. Upload your brand documents, select your content settings, and let hundreds of Market Brew agents deliver a 7-stage pipeline of optimized, linked, enriched content â boosted into orbit.
đ Sneak Peek: Light / Medium / Full Roast
This release also previews the new product line coming soon:
- Light Brew / Medium Roast â Self-serve experiences designed for teams who donât want to wander into the Lab, Roastery, or Enterprise complexity.
- Full Roast â Enterprise customers already know the next level: taking missions from orbit into outer space with Ranking Blueprints, Mission Plans, and CRM re-architecture.
Enterprise customers now get an early preview of this new experience, with a general release planned for the near future.
đĄ Why This Matters
- For Users Today: You can now take a keyword from concept to optimized content without leaving Market Brew.
- For Enterprise Customers: Get early access to explore the new Light and Medium experiences before public release.
- For Everyone Else: A clear glimpse of the future â SEO that feels like mission control.




âVisibility Launchpad â Hide Targets + Starred Custom Keywords
TL;DR: Clean up your Launchpad by hiding targets you donât care about, and instantly spot the keywords you added yourself with a â badge.
- Hide from view: In the Launchpad, you can now hide any target you donât want to consider right now.
- Not deleted: Hidden targets are simply tucked away; all their data remains intact.
- Manage hidden items: Use Show Hidden to review/unhide at any time.
Why it helps:
Reduces noise so you can focus on the target(s) you actually plan to launch against.
â
âHow to use:
- Open the targetâs header and choose Hide (or use the overflow ââŽâ menu, if present).
- Click Show Hidden at the bottom/top toolbar to restore.
2) Starred custom keywords
- â Badge: Any keyword you add manually now displays a star next to the term.
- Everywhere you work: The star appears in the Launchpad tables, selection carts, and keyword details.
- Exports & sorting: The star status carries through sorting/filtering and appears in exports as a âcustom/added-by-youâ indicator.
Why it helps:
Quickly distinguish your hand-picked ideas from recommendations and imports.
â
âHow to use:
- Add keywords as usual; theyâll automatically get a â .
- Hover the star for a tooltip (âAdded by youâ), where supported.
Notes & behavior
- Safe to tidy: Hiding a target does not affect calculations, saved work, or downstream tasks; it only changes whatâs visible in your Launchpad.

Release Notes: Content Booster - Brand Bible (Stage 0)
đ New Feature: Brand Bible Generation
We're excited to introduce Stage 0: Brand Bible - a foundational step that ensures all your content generation is perfectly aligned with your brand identity from day one.
What's New
đŻ Comprehensive Brand Analysis
- Automatically extracts and structures your brand's voice, tone, visual identity, messaging standards, and style preferences
- Creates a detailed brand foundation that guides all downstream content generation
- Ensures consistency across all generated materials
đ Source Document Upload
âUpload your existing brand materials to inform the brand bible:
- Supported formats: PDF, DOCX, PPTX, TXT, MD, CSV, HTML, PNG, JPG
- File size limit: Up to 50MB per file
- Smart processing: Our system intelligently analyzes your documents to extract key brand elements
đ Intelligent Website Analysis
- Automatically discovers and analyzes your existing website content
- Downloads and interprets CSS files to understand your visual theming
- Incorporates your current brand presence into the analysis
âď¸ Default Management
- Set default source materials per customer
- Configure website-specific defaults
- Streamline your workflow with reusable brand settings
How It Works
- Upload Brand Materials - Add your brand guidelines, style guides, marketing materials, and other relevant documents
- Automatic Processing - Our AI agents analyze your materials and website to extract brand identity elements
- Structured Output - Receive a comprehensive brand bible in JSON format with metadata, brand identity, positioning, and messaging guidelines
- Content Generation - All subsequent content stages use this brand bible to maintain perfect consistency
The Result
Every piece of content generated will now align with your brand's:
- Unique voice and tone
- Visual identity standards
- Core messaging and values
- Target audience preferences
- Positioning statements
This update ensures that your brand's personality shines through consistently across all generated content, creating a more cohesive and professional output.





đ Visibility Launchpad Enhancements
We've added a few new features!
- Find Launchpad Easier â new menu link to go directly to the Visibility Launchpad.
- Add Any Keyword You Want â there's an add keyword button now that allows you to add any keyword you want to the list.
- Visual Enhancements â a more powerful illustration of your content gaps and missing pages.
â No action needed on your end...the system has already been updated and everything is live. Youâll simply notice the improvements as you continue using the platform.




đ Content Booster Available From AI Overviews Author
We thought we'd drop an easy way to create new content, right on your favorite embeddings content testing tool, AI Overviews Author!

đ New Status Page: Stay Informed About Market Brewâs Uptime
At Market Brew, we know that trust is built on transparency.
Thatâs why weâve launched a new public status page where you can easily monitor the availability and performance of our services in real time.
đ Check it out here: status.marketbrew.ai
This page will provide:
- Live service status across all core systems
- Incident updates if any disruptions occur
- Maintenance notifications so you can plan ahead
Our goal is simple: to keep you fully informed and confident that Market Brew is running at peak performance.
Thank you for being part of the Market Brew community...weâre committed to delivering both reliability and transparency every step of the way.
đ Big News: A Major Upgrade for Faster, Smoother Performance
Weâve just made a big investment in the backbone of our platform...upgrading our database servers to give you a faster, more reliable experience.
Hereâs what that means for you:
- ⥠Double the Processing Power â moving from our old setup to the new system means more speed when you need it most.
- đž 4x the Memory â smoother performance and fewer slowdowns, even when things get busy.
- đ Next-Gen Architecture â a more efficient and powerful foundation that will keep us ahead of demand as we grow.
â No action needed on your end...the system has already been updated and everything is live. Youâll simply notice the improvements as you continue using the platform.
This upgrade is part of our ongoing commitment to investing in the best technology, so you can stay focused on results without worrying about whatâs happening behind the scenes.
Thanks for growing with us. The best is yet to come. đ
đ Release Notes: Manual Ranking Blueprint Setup Enhancements
Weâve expanded the Manual Ranking Blueprint Setup workflow with powerful new capabilities to give you more precision and control in your ranking simulations.
đ Searcher Location (New!)
You can now specify the searcherâs location when building a Ranking Blueprint.
- Use the new Lookup Available Locations field to search and select from hyper-local regions (state, city, county, borough, even neighborhoods).
- The system applies this location to simulate how results appear for searchers in that area.
- This is a huge leap forward for local SEOâenabling you to test and optimize for hyper-local variations in search results.
Example use cases:
- Comparing ranking differences between âNew York (City)â vs. âMidtown Manhattan (Neighborhood)â
- Tailoring landing pages and content strategies for location-based campaigns
đŻ Force Target Landing Page
When entering a Target Landing Page, you now have a new option:
- Force This Target Landing Page: ensures your chosen page is included in the ranking analysis, even if Google currently ranks a different page from your site.
- This is extremely useful when:
- Launching new content from the Visibility Launchpad
- Testing realignment strategies for underperforming pages
- Validating SEO changes before they rank naturally
When unchecked, the system defaults to whichever page from your site naturally appears in the results.
âď¸ Location Hierarchy in Market Brew Models
To provide the most accurate simulation, Market Brew now applies location targeting in the following order of preference:
- Keyword/Query Location â if the keyword itself includes a location entity with lat/lng
- Searcher Location â if no location entity is in the query, but a searcher location is defined
- TSEE Location â if neither keyword nor searcher location is available, the broader Target Search Engine Environment (e.g., Google US) applies
This ensures your simulations mirror the exact context of how Google interprets location signals in search.
â With these upgrades, you now have granular control over where the search is simulated from and which page is evaluated, unlocking new opportunities for local SEO dominance and content realignment strategies.


đ Release Notes: Visibility Launchpad
Launch Your Visibility Into Orbit
The Visibility Launchpad is Market Brewâs newest tool for identifying and prioritizing your siteâs most valuable content opportunities. It shows you where your coverage is weak, what keywords youâre missing, and how to fix those gaps with the biggest impact.
đ Whatâs New
1. Pinpoint High-Value Content Gaps
- Compares your site against real-world search demand.
- Surfaces opportunities ranked by search volume, CPC, and semantic similarity.
- Provides a clear Opportunity Score so you know exactly where to focus first.
2. Immediate âFixâ Options for Every Gap
For each content opportunity, you can take direct action right inside Launchpad:
- Content Booster â Generate optimized, search-ready content aligned with Market Brewâs ranking signals.
- Create Ranking Blueprint With Target Page â Build an optimization strategy tied to an existing page.
- Create Ranking Blueprint With NO Target Page â Launch a new page strategy from scratch.
3. Accessing the Launchpad
- Available from the AdShifted Tool or from the Analysis Group screens under Data for each website.
- To enable: simply recrawl your site and allow at least one of its Ranking Blueprints to recalculate.
đŻ Why It Matters
With Visibility Launchpad, teams can:
- See exactly whatâs missing in their content strategy.
- Take immediate, guided action with built-in fix options.
- Focus on the highest-value opportunities instead of chasing noise.
â Key Message
The Visibility Launchpad transforms raw search opportunities into a clear, actionable roadmap. No more blind spots, no wasted effortâjust precision targeting of the gaps that matter most.
đ Itâs not just visibility dataâitâs your launch sequence for growth.

đ Release Notes: Content Booster
Overview
Market Brew is proud to introduce Content Booster, the new system-wide orchestrator that unifies every major component of our search engine modeling ecosystem. Unlike standalone AI writers, Content Booster serves as the control tower for embedding intelligence, passage-based ranking models, link equity algorithms, and entity/schema enrichment tools â delivering content that is competitive by design, and validated against Market Brewâs predictive models.
This release ties together the full optimization loop: PPC â AdShifted â Ranking Blueprint â Visibility Launchpad â Content Booster â Visualizers (AI Mode, AI Overviews, Spotlight, Link Flow), enabling SEOs to go from competitive gap detection to ranking-tested deployment inside a single ecosystem.
Access Points
Content Booster can be launched from multiple locations inside Market Brew for maximum workflow flexibility:
- AdShifted Tool â Run Content Booster directly after identifying high-value PPC-to-organic keyword opportunities.
- Visibility Launchpad â Activate Content Booster from visibility distribution insights.
- Main Menu â Access Content Booster as a standalone tool for direct content optimization.
New Workflow
Content Booster introduces a six-stage workflow, each stage editable and requeueable at any point:
- Content Opportunity & Strategy â Define queries, audience, tone, and linking strategy.
- Brief & Structure Generation â Create an SEO-optimized outline with headings and semantic clusters.
- Draft Generation â Produce an AI-driven first draft aligned with style, tone, and embedding constraints.
- Optimization & Alignment â Embedding analysis, section parsing, cosine similarity scoring, selective optimization, and SEO enhancements.
- Internal Linking & Entity Enrichment â Insert internal/external links and schema markup via Spotlight.
- Quality & Compliance â Grammar, plagiarism, accessibility, and brand voice verification.
Key Benefits
- Closed-Loop Optimization: Direct path from keyword opportunity â content creation â ranking test.
- AI with Guardrails: AI generations are constrained by embeddings, clusters, and search engine model signals.
- Smart Linking & Schema: Integrated link equity modeling and entity graph enrichment.
- Compliance Ready: Final checks for grammar, plagiarism, and accessibility before deployment.
Availability
Content Booster is available immediately to all Market Brew users.
Future versions will add deeper Blueprint integration, customizable similarity thresholds, and expanded entity schemas.
⥠Next Step: Start from AdShifted, Visibility Launchpad, or the Main Menu to launch Content Booster and experience the full six-stage workflow.



- You can now filter the Business Name column using a clean dropdown menu â no need to type.
- The dropdown shows all available business names in alphabetical order.

New Feature: Understand Rankings Like Never Before with the New âQuery Scoreâ Column
- A new Query Score column has been added to the Ranking Blueprint screen.
- This score represents the master ranking score that powers the entire model â the higher the score, the closer the site aligns with the target query.
- Unlike Googleâs black box, Market Brew lets you see the exact ranking distances between competitors.
- This transparency makes SEO forecasting more precise than ever â now you can calculate exactly how far you need to go to take the lead.
Want to know whatâs holding you back from the top spot? Now you can measure it.

Flight Engineer Task Hours Update
All tasks have now been updated to use your Flight Engineer's task hours, which can be managed and adjusted under Crew Settings in your Flight Engineer account. This ensures that every task reflects the most accurate and personalized time allocations for your projects.
Coming Soon:Weâre introducing a detailed breakdown of time allocations, allowing you to specify Technical Hours, Marketing Hours, and Consulting Hours for each boost factor. This will give you a sharper lens on where your efforts and resources are being applied.
AdShifted v0.7 Has Been Released:Â Smarter PPC Replacement Planning Starts Now
- We've redesigned the AdShifted workflow to make planning more intuitive and interactive.
- You can now simulate different PPC replacement scenarios directly in the tool.
- Adjust the % Traffic Replaced per Month and the % You Will Pay Instead to instantly see how billing changes based on growth.
- Whether you're easing into organic traffic or going all-in, you can model it all â no spreadsheets needed.
This update makes it easier to compare PPC spend with SEO investment and build a plan that fits your goals and budget.



NEW TOOL RELEASED: Missing Pages Finder
What It Does
âCompares your siteâs content against the link flow distribution of top competitor sites, surfaces the highestâvalue competitor topics, and pinpoints the pages or topics your site is missing or underâsupporting.Highlights
- Link Flow Share: ranks competitor topics by their link flow share
- Top Competitor Page: click to open its AI Overviews Visualizer and inspect the embeddings driving its high score.
- Competitor Anchor Text: click to see the competitor pages using that anchor text
- Most Similar Page: shows your siteâs closest matching page by cosineâsimilarity; click to view its embeddings.
- Similarity Score: percentage score indicating how closely your content aligns with the keyword focus.
Quick Workflow
- Select your domain
- Run Missing Pages FinderâMarket Brew pulls top scoring competitor topics and compares to your site.
- Drill Down via clickable links to understand competitor context and your page matches.
- Act on truly missing or lowâscoring topics by creating new pages or reinforcing existing ones.
Why Youâll Love It
- Prioritized Gaps: Turn competitor strategies into an actionable content roadmap.
- Deep AI Insight: Go beyond keywordsâuse cosineâsimilarity to match topics by meaning.
- Seamless Exploration: Oneâclick access to visualizers and link lists for fast analysis.
Availability
âNow live for all Market Brew license holders, for all new Ranking Blueprints.

New Feature: Direct Target Page Scoresheet Links Now Available
Target Page Scoresheet Shortcut
Location: Ranking Blueprint > Data Menu
Overview
Weâve added a convenient shortcut to the Target Page Scoresheet for every target page directly within the Ranking Blueprint interface. This allows users to instantly open the scoresheet for their target URL without navigating through multiple layers of the UI.
Benefits
* Faster Access: Jump straight to the detailed scoresheet of your selected target page.
* Improved Navigation: Located within the Data dropdown for seamless workflow.
* Streamlined Analysis: Easily verify on-page issues and alignment with the Ranking Blueprint expectations.
How to Use It
* Go to any Ranking Blueprint.
* Click the âDataâ button at the bottom left.
* Select âTarget Page Scoresheetâ from the dropdown.
* The scoresheet for the target URL will open directly.
This enhancement is part of our ongoing efforts to reduce friction in the optimization process and make actionable insights more accessible with fewer clicks.

New Feature: Archived Optimization Tasks Now Available in History
Feature: Optimization Task Archiving
Location: Ranking Blueprint History > Snapshot Actions
Overview:
Previously, recalibrating a Ranking Blueprint would reset all Optimization Tasks â erasing your task progress and history. With this update, Optimization Tasks are now archived automatically at each recalibration and can be reviewed from the Ranking Blueprint History screen.
What's New:
* Task Archiving: All Optimization Tasks are now preserved when a Ranking Blueprint is re-calibrated.
* Historical Insight: View what was completed at each point in time â great for progress tracking and accountability.
* Easy Access: Just click the green âOptimization Tasksâ icon next to any snapshot in the Ranking Blueprint History view.
Why It Matters:
* Track changes and improvements over time.
* Retain a historical record of completed work.
* Avoid losing context when recalibrating Ranking Blueprints.
This update is part of our broader mission to make SEO efforts transparent, measurable, and iterative.

AI Mode Visualizer Enhancement
Weâve enhanced the AI Mode Visualizer by adding Template URL support. Now you can easily specify a âtemplateâ webpage to analyze, streamlining how you reuse a reference URL across multiple prompt tests.
How the Template URL Enables Reverse Engineering of Fan-Out Prompts
The Template URL feature in the AI Mode Visualizer allows you to load a specific piece of content â typically a published webpage â as the baseline for prompt generation. Once the page is loaded, the system can analyze its text and embeddings to determine what advanced research prompts (fan-out prompts) could have led to or matched this content.
In other words, instead of starting with a master prompt to fan out new prompts, you start with the content itself, and the system uses it to infer:
* What kinds of exploratory research questions or comparisons would an LLM (like Googleâs AI Mode) have needed to answer, that this page satisfies?
* Which deep or complex prompts would have retrieved or matched this content from a semantic perspective?
* How might a strategist have broken down the topic to arrive at this page as an answer?
By setting a Template URL, you are essentially telling the system:
âGiven this page, reverse-engineer the prompts that would have discovered or justified it.â
This is powerful for:
* uncovering gaps in your coverage
* stress-testing whether your page would satisfy different high-level user intents
* and planning future topic expansions.
Enhanced Content Blended Similarity in Ranking Blueprints
The Template URL feature in the AI Mode Visualizer is now linked directly from all new Content Blended Similarity Tasks inside Ranking Blueprints.
When analyzing an outperformer landing page (for example, a top-ranking competitor), you can now:
* Set the competitorâs page as the Template URL â this loads its content as the baseline.
*Â Reverse-engineer the fan-out prompts that would semantically justify or retrieve that outperformerâs content.
* Use those prompts to build or refine your own blended similarity tests in your Ranking Blueprint.
This workflow helps you:
* Understand why the outperformer page ranks from a semantic-intent perspective
* Identify what deeper research questions their content answers
* Design content or topic expansions that target the same semantic cluster
* Calibrate your internal linking and page focus to match (or exceed) their coverage
By using the Template URL with your content blended similarity task, you gain a systematic way to deconstruct a winning competitor page and reconstruct an even stronger strategy in your own content ecosystem.


Webpage Scoresheet Upgrade
We are excited to announce new enhancements to the Webpage Scoresheet screens within the Content Analysis module. These updates are designed to give you deeper, more actionable insights into your content duplication and clustering analysis:
External Links Addedâ
All duplicate page listings in both the Content Embedding Duplication and Top Embedding Cluster Duplication views now include external link icons. This allows you to quickly navigate to the duplicate pages for easier inspection and validation.
Direct AI Overviews Visualizer Access
You can now click on any % Similarity value in the scoresheet to launch the AI Overviews Visualizer.
For Content Embedding Duplication: This shows you the blended similarity view, directly highlighting duplicated segments within the full embedding space.
For Top Embedding Cluster Duplication: This will display the cluster analysis view, specifically comparing Cluster #1 from the source page against Cluster #1 from the duplicate page, helping you understand the most impactful cluster overlap.
These enhancements make it faster and simpler to trace, review, and remediate duplicate content issues with precision.


- Introducing Your New Notification System!
Weâre excited to roll out our new event-driven notification system, designed to keep you fully informed about your Ranking Blueprints and crawl activities.
With this upgrade, youâll get timely and actionable notifications for these events:
*Â Calibration Notifications
- Calibration Success: Your blueprint calibrated successfully
- Calibration Partial Success: Calibration completed but without target site
- Calibration Failed: Calibration ended unsuccessfully
*Â Snapshot Notifications
- Snapshot Complete: Your blueprint has been successfully processed
*Â Crawl Notifications
- Crawl Hold: Crawling paused due to error with target site crawl
- Crawl Release: Crawl hold released and resuming
- Crawl Retry: A failed crawl was retried
- Crawl Inbound Complete: Inbound link analysis is complete
- Crawl Crawl Complete: Primary crawl step has completed
- Crawl Outbound Complete: Outbound link analysis is complete
- Crawl Analyzer Complete: Crawl data analyzer process finished
- Crawl Complete: All crawl steps finalized
- Crawl Error: A problem occurred during the crawl process
Whatâs new for you?
*Â Real-time event tracking with clear status updates
*Â Simple acknowledgment â mark notifications as reviewed to stay organized
*Â Improved detail on crawl and calibration outcomes so you can act faster
*Â Streamlined monitoring of Ranking Blueprint activities
Look for the Notifications tab on your Ranking Blueprint screen, where you can see unacknowledged events at a glance and quickly drill into the details.
We hope this enhancement makes it easier than ever to keep your Ranking Blueprints performing at their best. As always, your feedback is welcome!


- Free Tools now works around 403/TIMEOUT errors
We upgraded our free suite of tools to automatically retry requests that are blocked (403 / TIMEOUT).
- New Feature Release: Compare Calibrated Rankings vs. Todayâs Reality
Weâre excited to announce a powerful new update to the Ranking Blueprint dashboard in Market Brew!
Introducing: Calibrated URLs Comparison View
Now you can visually compare the rankings as of the last model calibration against the current rankings today â side by side.
Whatâs New
*Â Side-by-side list of URLs â see exactly how search results have shifted since your last calibration.
*Â Helps identify which rankings were stable, which dropped, and which emerged after re-calculations.
* Use this insight to fine-tune your calibration strategy or diagnose volatility in the SERP landscape.
Available now inside the Calibrated URLs tab of every active Ranking Blueprint.
âPro Tip: If your target URL dropped since calibration, head to the Task Simulator and forecast your way back to the top.

- New Feature: In-App Bug & Feature Reporter (with Auto-Screenshots)
We're excited to announce a new way to make Market Brew even better â together. You can now report bugs or request features directly inside the app using the new floating comment icon in the bottom right corner of your screen. Â
Whatâs Included:
* Submit feedback right from the current page
* Automatic screenshots of your current view URL + user details pre-filled for faster resolution
* Reports are instantly posted to our internal Slack channel for real-time triage
No more support tickets, no context lost.
Just click, describe the issue or request, and hit Submit â weâll handle the rest.


- New Feature: Crawl Error Insights
â
You can now identify pages skipped during crawl due to critical crawling issues. These pages arenât blocked or 404, but failed due to other errors like 403 and TIMEOUT.
Available now under "Crawl Listing" in:
â
* The Ranking Blueprint Data dropdown (next to each site)
* The Website Dashboard under âActionsâ
Fixing these pages can improve crawl coverage and help recover lost visibility. And for sites with lots of 403 or TIMEOUTs, you can enable the proxy crawl for a better overall crawl.




- đşď¸ New Feature: Spotlight Atlas đşď¸
Explore the Geographic Footprint of Your Content with Spotlight Atlas!
Your site mentions places â cities, countries, regions â sometimes directly, often implicitly. Spotlight Atlas visualizes the top location entities extracted from your pages and maps them across the globe.See where your content resonates, clusters, and repeats â all from a semantic perspective.
Spotlight Atlas reveals the geographic focus of your websiteâs content â powered by Market Brewâs third-generation entity classifier. By extracting the top location entities from each page and mapping their centroids, Spotlight Atlas offers a clear visual of how your content aligns with real-world places.
See which topics dominate by region, drill into specific paths, and uncover hidden patterns in your siteâs semantic footprint.
Key Benefits:
â
â Map Every Page â Each dot represents a semantic centroid from your contentâs top location mentions
â Powered by Spotlight â Uses our proprietary entity classifier to extract accurate geographic references
â Visualize At Scale â Zoom in on content clusters or explore global coverage
â Clickable Paths â Inspect exactly which content contributes to each point
â Semantic Navigation â Ideal for teams optimizing international, local, or regional search relevance
You can find this NOW on all Ranking Blueprints under the "Data" Dropdown, and also on all Website Dashboards under the "Actions" Dropdown!




- đ New Feature: CPC Value Forecasting Now Live in the SEO Forecasting Calculator!
The SEO Forecasting Calculator just got even smarter.
â
You can now see the equivalent CPC value increase based on the cost-per-click (CPC) of the query you're targeting. This means youâll not only see how many additional visitors your improvements could bring, but also how much those visitors would have cost if you were buying the traffic through Google Ads.
Why it matters:
This update helps bridge the gap between organic SEO performance and paid media value, making it easier to justify SEO investments with concrete, dollar-based ROI metrics.
Whatâs Included:
đ CPC Value Increase Metric â Calculated in real time using your modelâs traffic improvement data and the CPC of your keyword.
đ¸ Clearer ROI Insights â Know exactly how much Google would have charged for the traffic youâre earning through optimization.
â Automatic Display â If Market Brew has CPC data for your keyword, the value appears automatically in the Forecasting Calculator.

- đ New Feature: Task Hours Now Visible & Actionable
Each task can now be associated with an estimated number of hours required to complete it. This enhancement gives Flight Engineers the ability to:
ââ Understand the time investment required per task
â Evaluate task leverage more effectively
â Prioritize based on effort vs. impact
â Get a clearer picture of potential expenses when allocating resources
đ What You Can Do
â Filter tasks based on the hours required (e.g., "Show only tasks under 5 hours")
â Sort your task list by effort (from lowest to highest hours, or vice versa)
â
This added dimension helps Flight Engineers make smarter, faster decisions when managing optimization strategies.


- đ Expertise Factor Task Upgrade
Now with Detailed Topic Coverage and Content Suggestions. Weâve supercharged the Expertise Factor Score Task to make it more transparent and actionable than ever.
Whatâs New:
â Breakdown of Topic and Sub-Topic Coverage: the Expertise Factor Score now includes a detailed analysis of how well your page content covers each Spotlight Focus topic cluster and its associated sub-topics. For every entity in the cluster, you'll see a coverage percentage, helping you pinpoint weak areas at a glance.
â
â LLM-Powered Content Suggestions: for each undercovered entity or sub-topic, the system now provides targeted content suggestions generated by an LLM â tailored to help you increase the Expertise Factor Score with relevant, authoritative content.
â
â Direct Link to Spotlight Focus Alignment: because the topic cluster is derived from Spotlight Focus, the system now warns you if the underlying focus appears misaligned. Fixing Spotlight Focus first will ensure youâre optimizing for the right semantic space.
Why It Matters:
This upgrade turns the Expertise Factor Task into a content strategistâs dream â surfacing not only whatâs missing, but exactly what to add. Itâs precision-guided topical authority, powered by real entity clustering and LLM analysis.

- đSemantic Link Scoring: Advancing the Reasonable Surfer Model
đ§ Summary
As part of our continued migration from the Random Surfer to the Reasonable Surfer model of link analysis, weâve upgraded the link scoring algorithm to incorporate semantic relevance using content and anchor text embeddings.
This refinement reflects how modern search engines evaluate the contextual value of linksânot just their presence.
đ Whatâs New
â1. Anchor Text vs. Page Semantics:
Every linkâs anchor text is now embedded and compared to the semantic representation of the destination page. This produces a cosine similarity score that models how aligned the anchor is with the content it points toâgiving preference to links that genuinely describe their targets.
â
â2. Top Cluster Centroid for Content Matching:
Rather than treating the entire page as a single semantic unit, we segment each page into 700-character content chunks and apply k-means clustering (k=3) to those embeddings. We then use the centroid of the top clusterâthe most thematically consistent region of the pageâas the true semantic representative. This significantly improves precision, especially for long-form or multi-topic pages.
đ Why This Matters
The Random Surfer model treats all links on a page equally. Our existing algorithm had already taken steps toward the Reasonable Surfer modelâfactoring in things like font size, editorial status, and duplicative anchor text.
This latest upgrade goes further by incorporating semantic alignment, bringing our link modeling in line with how todayâs AI-enhanced ranking systems operate. Links are no longer just weighted by structureâtheyâre judged by how well the anchor text matches the destinationâs meaning.
This results in more accurate link flow distribution, improved link prioritization, and ultimately, a better simulation of how real-world algorithms value internal and external links.
Link Relevancy scores are shown on all Link Scorecards, accessed by viewing a link listing, and then clicking on the scorecard icon on the left of the link row.

- đ AI Mode Visualizer â Major Update (June 2025)
Weâve officially rebranded the SEO Similarity Matrix tool as the AI Mode Visualizer â with a suite of powerful upgrades that bring you one step closer to understanding how Googleâs AI Mode ranks content.
đ§ New Features:
âLLM-Based Prompt Generation
â Enter a single master prompt, and our system will automatically expand it into multiple related prompts using LLM-style âfan-outâ â just like Googleâs AI Mode does before scoring content.
âInteractive Similarity Matrix
â Each cell in the matrix displays the cosine similarity score between a passage and a prompt.
â Click any score to open the AI Overviews Visualizer and see exactly how that content chunk aligns with the selected query.
âImproved UI / UX
â Prompts now appear in individual input rows for easier management
â Add/remove prompts dynamically (up to 10)
â Clearer labeling of master prompt and generated prompts
â Simplified layout and legend styles
â Updated call-to-action: âVisualize AI Mode Coverageâ
đ Updated Instructional Content:
â New âHow to Use the AI Mode Visualizerâ section on the tool page
â Revised onboarding flow for prompt generation
â Updated video tutorial and script to match new branding and functionality
đ This update helps you simulate how Googleâs AI Mode breaks queries into multiple intents, compares those intents against your content, and selects the most semantically relevant passages â all before any traditional ranking signal comes into play.
đ§Ş Itâs the first public tool that visualizes AI Modeâs passage-level thinking.
đşAI Mode Visualizer Tutorial

- New Ranking Factors: Embedding-Based Page Similarity Now Available
âWe're excited to introduce two powerful new ranking factors available in all new Ranking Blueprints:
âPage Embedding Similarity: This measures the cosine similarity between full-page embedding centroids, identifying near-duplicate pages across your site.
Top Cluster Similarity: This metric analyzes and compares the core thematic embedding clusters of each page â a powerful way to spot overlapping topics and potential keyword cannibalization.
After a re-crawl, each website now includes a new worksheet in the downloadable Website Reports, displaying all pairwise similarity scores between pages. These new metrics are also shown in the Webpage Scoresheet, with a new tab adjacent to the Keyword Duplication tab.
These new factors aren't just academic: high duplication is a red flag in Googleâs site quality evaluation, and these metrics surface the hidden redundancies dragging your site down. Duplicate or semantically overlapping content splits authority and lowers individual page performance.
Worse, it creates internal link loss: wasted link flow flowing into multiple similar pages, which act like "dead ends" in the link graph. With too many redundant nodes, your PageRank gets diluted, and fewer high-value pages earn prominence.
These issues often go unnoticed â until now.


- Ranking Blueprints are now "frozen" after calibration. This means that re-crawls will NOT automatically trigger a re-calculation of the tasks and forecasting models. You can re-enable this automatic re-calculation after re-crawl on the refresh dropdown.

- Additionally, each site whose recent data is not included in the current Ranking Blueprint is identified next to the "Last Crawled" column.

- Top Locations By Frequency has been added to all Spotlight screens. The maps show the top 3 locations by weighted occurrences, and the "bullseye center" that is calculated. This is the page's location centroid that is used in the location algorithm to find the levenshtein distance to the user query.


- Location on Spotlight screens has been updated to correctly reflect the Location Ranking Factor used in the model. The top 3 location entities by occurrence are used to compute an average lat/lon location for the page.
- Calibration for Ranking Blueprints with no target site specified has been greatly improved. Prior to this, the Ranking Blueprints would not add more than 4 sites and would stop calibration without attempting to add more sites to the model. Succuessful calibrations have been increased by 40%.
- Bug fixed where Ranking Blueprints with no target site were not showing the radar plots and the current rankings column.
- Re-calibration of all Ranking Blueprints has been greatly improved. The decision tree of tried combination of sites is more thoroughly explored resulting in a 20% increase in calibration rate.
- Similarity Column has been added to the XLS/PDF download in the Website Embedding Listing screen.
- Duplicate Content Ranking Factor precision has been improved.
- Mission Plans now sort by PSO score. See your most calibrated Ranking Blueprints first.
- Video Tutorials now available directly from the user menu.
- Rendered HTML now available on all Webpage Scoresheet screens. See what the Market Brew JavaScript rendering engine did to the HTML, and see what Google sees.

- Link Flow Distribution screen updated. Renamed to Internal Link Flow Distribution, the screen now shows each page's Net Total Link Flow in addition to its Internal Link Flow Distribution %. Net Total Link Flow includes both external and internal incoming Link Flow shares, whereas the Internal Link Flow Distribution % shows where the site's External Incoming Link Flow goes once it enters the site.

- Ranking Blueprint Manual Setup now supports multiple keywords. Enter up to 10 keywords at a time, separated by commas.

- There is now a WYSIWYG editor for both the AI Overviews Author and Spotlight Author tools. You can now edit in both raw and rendered HTML.

- For logged in users, AI Overviews Author is now available directly without a URL. This feature can be used for content that is not yet deployed to a URL.

- Teams are now called Mission Plans. A Mission Plan is the Flight Path that emerges when we model multiple Ranking Blueprints. The overlap reveals the gravitational forces that control ranking across every page layout. Accounts are now called Crew. And your Dashboard is now called Mission Control.
- New Feature: LLM-Powered Analysis of Market and Spotlight Focus Differences. We've added a powerful new AI-driven analysis to help users understand the key differences between the Market Focus and Spotlight Focus algorithms when comparing a Target Page to an Outperformer.

- FREE Link Spotter Tool Launched. Find the best spots to link back to your most important pages. Link Spotter leverages the power of AI to analyze and recommend optimal link placements to a target page. Simply input a target page and up to five source pages, and Link Spotter will identify contextually relevant chunks of content within those pages to create high-impact links. Save time, improve your internal linking strategy, and enhance user experience and SEO with precision-driven recommendations.




- FREE SEO Similarity Matrix Tool Launched. The SEO Similarity Matrix tool allows you to compare the semantic similarity between multiple keyword embeddings and a webpage's content embeddings. This can help you understand how different sections of the page's content stack up against root and long-tail keywords. Enter a URL and up to 10 keywords to create a matrix of cosine similarities. This will calculate the average cosine similarity of each embedding chunk of content on the page, for each keyword.

- Free Additional Credits for all public tools. Our growing suite of FREE tools now allow for an additional request credits by linking to the tool from your website.

- Improved Ranking Blueprint Calibration. The Particle Swarm Optimization (PSO) process the drives the calibration of Ranking Blueprints has been improved, specifically the seeding algorithm that chooses which sites to add to each Ranking Blueprint.
The PSO score range has effectively more than doubled, putting the highest calibrated Ranking Blueprints around 15,000 (highest before was around 7,000). This new scoring system will better distinguish Ranking Blueprints that have more sites above the target, as well as sites in higher rankings. - Improved Proxy System. The proxy system has been upgraded. No region is required when selecting a proxy crawl for a particular site. Simply turn on the proxy system and it will determine the best region to crawl from. Additional rendering capabilities have also been implemented with the proxy system, making the proxy crawls both more reliable and more precise.

- Top Cluster Similarity (Tasks). The Top Cluster Similarity algorithms (aka Parasite SEO) now produce full explanations on why your target content does NOT appear in the page-level or site-level Top Cluster, including steps to fix the content.
To pickup these new task explanations, visit any Ranking Blueprint and click "Re-calculate Tasks" under the Actions dropdown.

- Link Flow Finder (Embeddings). The Link Flow Finder has been upgraded to use the Webpage's Top Embedding Cluster, replacing the previous implementation that used the Webpage's Market Focus.

- Website Embedding Listing. The Website Embedding Listing has been upgraded to include the ability to filter by a group of URLs or by a group of Embeddings. Filtering by URL produces all embeddings from those pages, and does a k-means clustering. Filtering by embeddings produces all embeddings similar to those embeddings. If multiple embeddings are used, the centroid of those embeddings are used to retrieve similar embeddings.

- Link Flow Distribution Task. The Link Flow Distribution task is now upgraded to use the Ranking Blueprint's keyword to retrieve list of suggested internal links.

- Ranking Blueprint DOM Embedding. The Ranking Blueprint DOM Embedding screen has been updated to show the DOM Clusters for that Ranking Blueprints in the same legend as the AI Overviews Cluster tab. Users can now visualize which DOM structures are associated with higher rankings in that SERP.

- DOM Embeddings. The Document Object Model (DOM) represents the structure of an HTML document as a tree of objects. Each node in the tree is an element on the web page, such as headers, paragraphs, images, and links. DOM embeddings take this structural information and convert it into a numerical format. By embedding the DOM structure, we can compare and analyze it systematically.
Users have the ability to view and analyze DOM embeddings through Market Brew's free AI Overviews Visualizer.

- DOM Embedding Cluster Algorithm. This innovative approach involves nd analyzing the Document Object Model (DOM) structures of web pages as they appear in the Search Engine Results Pages (SERPs). By stripping content from the DOM, embedding it, and associating these embeddings with specific rankings, the algorithm calculates a DOM embedding cluster score. The scores are then used to identify which structural elements Google tends to favor, providing a new layer of insight beyond traditional SEO metrics.
Read more on Unlocking Google's Bias: How DOM Embeddings Reveal Preferred Page Structures.

- DOM Embedding Listing. All Ranking Blueprints and their DOM embeddings can be explored by viewing the DOM Embedding Listing screen:

- Webpage Level DOM Embedding. Individual DOM embeddings can be viewed through both the DOM Embedding Listings screen, or directly from the Ranking Blueprint:


- Modeling Google's AI Overviews. The SGE Visualizer has been updated to model Google's AI Overviews.
- Modeling Site-Level Parasite SEO. A new algorithm, based on embeddings, is introduced into the search engine model.
Called Top Cluster Similarity (SUBDOMAIN), or shown as "Top Cluster (Site)" on the SGE Visualizer, it is site-level algorithm that looks for the embedding chunk with the highest cosine similarity for the query, and updates the similarity depending on whether or not that embedding chunk is also found on the site's top embedding cluster.
Pages that aren't related to the site will receive lower scores because of this algorithm. This can be considered a site-level Parasite SEO filter.

- Site Cluster #. A new metric is being captured for all new crawls. After converting content to embedding chunks, each embedding chunk now receives a site cluster #, depending on the k-means calculation of all embedding chunks on that subdomain. In addition to using this in the Top Cluster Similarity (SUBDOMAIN) algorithm, users can also view this metric on the Website Embedding Listing screen, under Result Cluster.

- Modeling Page-Level Parasite SEO. A new algorithm, based on embeddings, is introduced into the search engine model.
Called Top Cluster Similarity, it is page-level algorithm that looks for the embedding chunk with the highest cosine similarity for the query, and updates the similarity depending on whether or not that embedding chunk is also found on the page's top embedding cluster.
Content chunks inserted into a page that aren't related to the page will receive lower scores because of this algorithm. This can be considered a page-level Parasite SEO filter.

- Page Cluster #. A new metric is being captured for all new crawls. After converting content to embedding chunks, each embedding chunk now receives a page cluster #, depending on the k-means calculation of all embedding chunks on that page. In addition to using this in the Top Cluster Similarity algorithm, users can also view this new metric on the Website Embedding Listing screen.

- Spotlight Visualizer. A FREE limited version of Spotlight has been released to the public. This is the second visualizer representing the entity-based semantic classifiers in modern search engines, with the SGE / Embeddings Visualizer being the first.


- Spotlight Author v2.0. An updated version of Spotlight Author has been released. This tool is also available to the public.

- Ask Calvin v2.0. Thousands of real Market Brew customer service responses have been now included in Calvin's context window. Ask any question you have about Market Brew or SEO in particular.
- SGE Author. Users can now test their HTML in real-time to see which version works the best with embeddings. This testing tool is one of the core SEO tools for beginning to explore how search engines include your cntent ( and their embeddings) in its ChatGPT-like (Large Language Model) response called the Search Generative Experience (SGE).


- First Input Delay Deprecated. Following Google's decision to remove First Input Delay (FID) and replace it wit Interaction to Next Paint (INP), Market Brew has removed FID and Domain FID from the list of available algorithms in all new Ranking Blueprints.
- Content Blended Similarity. Following the deployment of the Content Similarity Score and its algorithm inside all Ranking Blueprints, we now introduce a different scoring methodology: an average across all embedding chunks. The SGE Visualizer has been updated with this new metric (Avg. Similarity):

- All new Ranking Blueprints include Content Blended Similarity. Tasks will automatically show the breakdown of the score for your target page vs. the outperformer.
Clicking on the Content Blended Similarity percentage will take you to the SGE Visualizer, whereas clicking on the Embedding Chunk Offset will take you to the individual Embedding Chunk screen, complete with a breakdown of extracted entities and topic cluster for that specific chunk.

- Website Embeddings. From the Website Dashboard screen, users can now search embeddings and get back a similarity score and a cluster group #. Clustering can be adjusted from 3-10 groups, and URLs can be filtered so that the embedding search / clustering is only done on that filtered group of URLs. If embeddings are not yet enabled, click "Actions" and "Re-Crawl".

- Centerpiece Annotation. All webpage embeddings now have a particular set of entities and topics, as well as a topic cluster. Just click on the eye icon to view. Future derivative algorithms will use this data.


- Heading Vector Algorithm. Google's purported Heading Vector Algorithm has been modeled and added to the list of default algorithms with each new Ranking Blueprint. Each H1...H6 tag is scored based off of a cosine similarity score for that tag and the query. H1 tags are weighted more so the similarity counts more. An average score is taken based on all H tags on that page. This new algorithm can be added by creating a new Ranking Blueprint and ensuring all sites have been re-crawled.
- META Title Embedding. All META Titles now have an associated similarity score. This is a cosine similarity between the META Title field and the query. This new algorithm can be added by creating a new Ranking Blueprint and ensuring all sites have been re-crawled.

- SGE on Market Focus and Spotlight Focus screens. The SGE Visualizer tool is now available directly from both Market and Spotlight Focus screens.
- Embedding Footprint. The SGE Visualizer tool has been upgraded to include a visual footprint of each embedding cluster. Each embedding cluster has a footprint. To create a unique footprint, we visualize the embedding vectors in a lower-dimensional space, projecting them onto a 2D plane using a technique called Principal Component Analysis (PCA).

- Embedding Cluster View. The SGE Visualizer tool has been upgraded to include a cluster map of each page. Each embedding block has been assigned to one of three groups, called the embedding cluster. This cluster is viewed as a group in many embedding search algorithms, and this cluster footprint is sometimes used during the machine learning process to recognize good or bad sites.

- Ranking Blueprint. The Analysis Group has been renamed to Ranking Blueprint.
- % Associated Link Flow. The Market Focus and Spotlight Focus algorithm screens now display % Associated Link Flow for a better understanding of what the incoming anchor text distribution looks like.

- Free SGE Visualizer Tool published. Use any URL to explore the beginnings of Search Generative Experience (SGE) modeling. It begins with a embedding visualizer that allows users to begin to understand how search engine LLMs might choose your content based on embeddings.


- Cosine Similarity Inspector Tool By Webpage. The Cosine Similarity tool has been added to the Webpage Scoresheet screens, under "Content Analysis" -> "Cosine Similarity Tool". Enter any search query and you will be taken to the Cosine Similarity Inspector Tool for that webpage, for the given query.

- Cosine Similarity Inspector Tool. Added top similarity score.

- Cosine Similarity Algorithm. The Cosine Similarity Algorithm has been added to the baseline search engine model. This algorithm models Sentence-BERT embeddings and Google's concept of Centerpiece Annotation. A cosine similarity score is calculated against segments of content on each page. Create a new search engine model to include this new algorithm.
- Cosine Similarity Tasks. Like other algorithms in the model, each landing page in the SERP is evaluated to input into the calibration process and receive its own bias/weight settings (called Boost Factors). When there is a high correlation, this task will be shown and both the target page and outperformer cosine similarity scores will be displayed, each with links to the Cosine Similarity Inspector Tool.

- Cosine Similarity Inspector Tool. An inspection tool has been created to analyze the embeddings.

- Location Algorithm Updated. Improvements to latitude / longitude coordinates for short queries.
- Core Web Vitals not set. CWV data that is not available for a particular URL will now be represented as the maximum range for that Core Web Vital. This was previously assumed to be the minimum range, causing tasks to erroneously show not set URLs as the best performing.
- Introducing Calvin, the first AI search engineer assistant in the world. Calvin is immediately available to all existing users. Calvin can analyze your search engine models, or any of the data on the Market Brew platform.
- One-Time Calibration is now default. When using the setup wizard, the one-time option is now selected as the default. This aligns with the best practices of our users, as most users want to manually re-calibrate the models.
- Performance Enhancements. Infrastructure investments continue to improve build time.
- Missing PSO Scores. Particle Swarm Optimization (PSO) scores that are missing on the Analysis Group Listing screen now have an informational icon and popup to warn users that these Analysis Groups have no PSO score assigned. This can happen if the Analysis Group is currently being setup, or if there was an issue with calibration.
- Model Rankings. The Model Rankings column on the Analysis Group screen was previously showing the rankings since last calibration. They now depict both the current rankings as of the last re-calculation / website re-crawl as well as the rankings at the time of calibration.
- Interaction To Next Paint. This Core Web Vitals metric has been added to the list of Boost Factors. Additionally located on the Website Dashboard and Webpage Scoresheet screens. All Core Web Vitals metrics are now pulling from Google's CrUX system, using the 75th percentile measurement, aggregated from the last 28 days.
- Password Reset. A bug preventing the password reset has been fixed.
- White Label Added. The Market Brew user interface is now able to be privately labeled (white label). Contact your representative for details.
- Custom SERP. Market Brew uses 3rd party ranking data to calibrate against. Sometimes that ranking data is incomplete. In those cases, select âCustom SERPâ under the TSEE options, and provide a list of valid URLs that the Analysis Group should use to calibrate against.

- Bulk Analysis Group Deletes. A performance issue was fixed when requesting bulk deletes.
- Similar Words. Market Brew's model of Google's Hummingbird system now shows the list of similar words in the alert emails during Analysis Group setup.

- Task Simulator. You can dial in the % completed for each task, forecast rankings / traffic against your search engine models. For instance, if you are unable to complete a certain task, or only partially able to complete it, you can see what will be necessary to achieve your desired new ranking.
Query Score, Ranking, and Traffic Improvements are instantly updated by adjusting the completion sliders for each task. Click the Raw Query Score improvement to view the Combined Search Listing screen to visualize how implementing the tasks will effect your new rankings.

- Task Simulator link added to Optimization Tasks screen. All optimization tasks screens that are filtered by Analysis Group will now have an option to forecast rankings / traffic.

- Calibration automatically turned off after Analysis Group setup. Auto self-calibration option has been removed. Now, each Analysis Group will turn off calibration automatically after setup. This workflow was used 95%+ of the time for users, as this was a necessary first step to begin A/B testing after calibration.

- Manual Calibration Option Added. After A/B testing cycle is completed, select "Calibrate Model" from the Refresh dropdown to re-calibrate the model against the updated rankings.

- Stale calibration alert added. Market Brew will bubble an alert if the Analysis Group hasn't been calibrated in more than 90 days.

- Tasks and Target Page's Query Score monitoring added. The overall task progress and the target page's query score improvement in the model rankings are now tracked on the Analysis Group screen, showing the improvements since last calibration.

- The Task Listing Screen has replaced the completed field checkbox with a progress bar. The progress bar will show how much each algorithm score has improved since last calibration. 100% means the gap has been completely closed between your target page and the outperformer page for that algorithm. Updates each time the Analysis Group is re-calculated. Progress bar will start updating once Analysis Group has been calibrated again.

- % Occurrences Column added to Market / Spotlight Focus screens. New column showing % occurrences can now be sorted/filtered.

- Pagination added. On Market Focus and Spotlight Focus screens, pagination has been added to the top of the lists.
- Similar Words alerts update. Similar Words alert emails were being sent each time a re-calibration was triggered. Now this email will only be sent once per Analysis Group.
- Social Links updated. Improved algorithm calculations in the Paid Link, Advertorial Link, and other areas. Links to maps.app.goo.gl will no longer be counted in these penalty calculations.
- Preferred Pages. Preferred URL "reset to default" option has been added on the website edit screen. This option will lookup every target page added to an Analysis Group and reset your preferred pages to this list.

- Link Neighborhood Tasks. Improved recommendations for all Link Neighborhood Tasks. Each task will now show both the outperformer's and target's incoming/outgoing links alongside their link flow values, for easier comparison. To pick up these new changes, re-crawl the sites that you wish to get this new detail.

- Link Neighborhood Penalties. Landing pages that had no incoming links were being incorrectly promoted in the model as having a good Link Neighborhood. We've adjusted this so pages with no incoming links will be worse than pages with incoming links. To pickup this new change, initiate a re-crawl for the site for which you wish to see this update.
- Advertorial Penalties. The advertorial penalties were showing the wrong percentage amounts in the task summary. The penalties were valid, but the percentages were not the values that were used in calculating the algorithm. Values have been updated and all new tasks generated will contain the updated figures.
- Spotlight Focus / Expertise Task Enhancements. Topics and keywords are now suggested to improve both the Spotlight Focus and Expertise scores. This is now viewable in all new generated optimization tasks and Conversation Reports. The Task Summary screens (Analysis Group -> Website Data Dropdown -> Task Summary) will also generate these on-demand.

- Market / Spotlight Focus UI Enhancements. Users can now access the Link Flow Finder directly from the Anchor Text tab in both the Market Focus and Spotlight Focus screens.
- Link Neighborhood Recommendations. The Link Neighborhood tasks and recommendations are now updated with more detailed descriptions of the Link Neighborhood.
- Query Score Breakdown. The Query Score Breakdown now shows 0-100% instead of 0-1 for all algorithm scores. The Query Score Breakdown screens can be viewed from the Combined Search Listing screen (Analysis Group -> Actions Dropdown -> Simulate a Search) by clicking the Query Score percentage next to any ranking result.
- Market / Spotlight Focus UI Enhancements. Users should see their Basket tab open by default now. The # of occurrences on the 1st tab is now sorted by default.
- Analysis Group Setup Emails. All users will now receive notices of Analysis Group setup issues. Previously only Solutions Engineers received these emails. These can be turned off on the Account Settings -> Email Notifications tab.
- Similar Words System Now Widely Available. Our Similar Words system, which models Google's Hummingbird (query expansion), is now editable by all users. This can be enabled / disabled and edited on the Analysis Group -> Settings tab.
- Major Spotlight Performance Enhancements. Users should see their Analysis Group setup times decrease by 60%-80% due to a major performance enhancement in the Spotlight algorithm, which taps into new software and hardware to generate topic clusters at scale.
- Delete All Teams + Analysis Groups: on both the Team Listing and Team screens, there is a new option to delete not only the Team, but also all underlying Analysis Groups. Useful for cleaning up Analysis Groups that were only used on a one-time basis.
- Inbound / Outbound Link Neighborhood Algorithm: previously added as Boost Factor. Now available on Task Listings and Analysis Group radar plots. Measures avg. link flow per page. Low values are showing correlation with decreased rankings.
- Advertorial Algorithm: previously added as Boost Factor. Now available on Task Listings and Analysis Group radar plots. Measures ratio of external / total editorial links. Designed to catch signatures of guest blogging or advertorial posts that are designed only to produce link flow share to a specific external site. High values are showing correlation with decreased rankings.
- "Paid" Links Algorithm: previously added as Boost Factor. Now available on Task Listings and Analysis Group radar plots. Measures ratio of external non-editorial / total non-editorial links. Designed to catch signatures of paid links or link selling. High values are showing correlation with decreased rankings.
- Competitor Backlink Reports now include "First Seen": available on Task Listings, for any AHrefs Domain Rank or Semrush Domain Rank optimizations, directly above Task Descriptions, now sortable by each link's first seen date.
- Canonical URLs now generate Tasks in each Analysis Group: Analysis Groups with a target URL that points to a canonical URL will now generate tasks.
- Competitor Backlink Reports now available in a clean XLS format: available on Task Listings, for any AHrefs Domain Rank or Semrush Domain Rank optimizations, directly above Task Descriptions.
- 22% increase in Particle Swarm Optimization accuracy: we've improved the machine learning models which calibrate your search engine models (Analysis Groups).
- Ahrefs Domain Rank: the existing Domain Rank Boost Factor was renamed to Ahrefs Domain Rank.
- Semrush Domain Rank: added Semrush Rank for Website as a new Boost Factor.
- Fixed Related Entities Bug: related entities in the Spotlight Focus screen were missing links to the Knowledge Graph.
- Added Ignore Backlinks Option: typically used when you are doing A/B testing and have a test site that is included, but also has lots of external incoming links from the same TLD production site. Found on the Website Settings screens.
- Added dedicated internal DBPedia servers: this performance enhancement will greatly increase the capabilities of the entity-based knowledge graph algorithms within your search engine model.
- Performance Improvements on Analysis Group Screen: this performance enhancement will greatly decrease the load times of Analysis Group screens.
- Added Delete button on Analysis Group: you can now directly delete any Analysis Group on the AG screen, located under the Actions drop-down.
- Added Billing Emails: on the Account Settings screen, on the Invoices tab, you can now specify additional billing emails that will receive a copy of the quarterly invoices.
- Performance Enhancements: we've added servers and enhanced the queuing algorithms to better serve our users.
- Activation Bug: we've fixed a bug related to activating new Market Brew accounts.
- Added No Pricing Tier Option: when creating Market Brew accounts, Resellers now have the option to disable any pricing tiers, and instead just pre-load the crawls / credits into the account.
- Added Analysis Group Button: on the Team and Account Settings screens, an "Add Analysis Group" button has been added.
- Added TSEE Ranking: on the Analysis Group screens, on each site data row, the Target Search Engine Environment (TSEE) ranking will now be updated to show both the the current ranking position and the ranking position at time of calibration.
- PSO Score on Analysis Groups: on all Analysis Groups, Analysis Group Listings, and Team screens, the Particle Swarm Optimization (PSO) score can now be found. A scale from 0 to 100% was created to inform users how well the model was calibrated compared to other models in the Market Brew system.
- Allow Manual Setting of Target URL:Â needed for A/B testing where you have a Test Analysis Group that is copied from the Production Analysis Group. Target URL can now be set once the production site has been swapped out for the testing site.
- Notification Preferences:Â we have updated the notification preference system, now found on the Account Settings screen under "Email Notification Settings"
- Added Location Algorithm:Â we have added a Location Algorithm as a Boost Factor. This will be enabled whenever there is a location entity detected within the query, and each page will detect location entities and create a centroid (Lat / Lon) based on those entities. This is particularly helpful with local SEO situations.
- Evergreen Chrome JavaScript Engine:Â we have updated the JavaScript parsing engine to automatically follow the upgrade path of the the public Chrome browser. Upgraded rendering as well as new Web Core Vitals scripting are the biggest features, with internal performance enhancements as well.
- UI Refresh: Market Brew has updated its user interface to a new, modern, high-tech dashboard, leveraging the latest in client-side JavaScript and asynchronous processing. Default settings have been chosen: dim mode + slim-plus menu, top-bar theme colored, green, profile mode popup. Users will be able to select their own settings, like dim or dark mode.
- Task System Refresh: Market Brewâs current task system will be expanded significantly and pushed to the Customer Home (top screen). While the previous task system relied on static alerts (shown on the SEO Alerts tab on Dashboard, Scoresheet, et al.), the new task system will rely heavily on the Biggest Weaknesses engine that drives the Simulation and Conversation Reports, but will also draw off of the existing Predictive Alerts and other subsystems. Tasks will introduce the concept of Categories, which will enable matching to different Team Roles (see below).New screens: Task -- shows the task, the category, the Query Potential, and options to complete the task. Workers will be able to mark the task complete, and also log how many hours they worked on the task. Market Brew may optionally add estimated hours to complete the task as well. Task Listing -- shows the list of tasks per Analysis Group. Includes Task hours / completed / assigned. Filterable by Category and Snapshot Date. Sortable by Query Potential. Team Tasks -- shows the list of all tasks per Team. Includes Task hours / completed / assigned. Filterable by Category and Snapshot Date. Sortable by Query Potential.
- Market Brew Teams: Teams enable accounts to set up and manage a task-based system that will be shown on the Home Screen of the new UI dashboard. Parent accounts will be able to create the following: Teams -- defined by Analysis Groups (AGs), each Team will give access to a list of AGs to its Workers. This will replace the current authorization scheme of assigning individual authorizations per AG. Existing workspaces will be converted to a Team. Teams will also be able to define specific Tasks that will be filtered out. Workers -- all child accounts will be converted to Workers. Workers can be assigned to multiple Teams, and will be assigned to one or more Roles. There will be a special type of Worker called Team Lead which will be assigned to a Team, and will have admin privileges for that Team (add/edit/remove Tasks/Workers) Roles -- Predefined Roles will exist out-of-the-box (Off-Page, On-Page, etcâŚ) but additional Roles can be created and assigned as necessary. Parent Accounts or Team Leaders can assign Worker Roles as necessary, but only Parent Accounts will be able to create / edit Roles.
The following Widgets will be shown per Worker on their Customer Home screen:
Target Sites -- links to Website Dashboards
Top Tasks -- for all Teams that Worker is assigned to, one widget will show # of Tasks available, and another will show top list of Tasks, with links to the individual Task screens
Tasks Completed (Progress Bar) -- shows how many tasks have been completed during current Snapshots. Tasks will be archived during each new Snapshot, and progress bar will reset according to new tasks that will be created. Filterable by Date Range.
Tasks Completed (Snapshot History) -- by default, shows any tasks that have been marked completed in the current Snapshot. Tasks will be archived with each new Snapshot, and the completed list will be reset. Filterable by Date Range.
All of the above can be filterable by selecting one or more Teams.
New Screens: Add / Update / Delete Teams, Add / Update / Delete Workers, Add / Update / Delete Roles
- Time Zone Selection:Â all accounts can now select their preferred Time Zone, located on the Account Settings screen.
- Schema.org LD+JSON:Â on the Spotlight Screens, a new (Schema) tab can be found that automatically generates the LD+JSON schema for that page.
- Spotlight Author:Â on-demand version of Spotlight added to main menu and Spotlight screens.
- Particle Swarm Optimization 2.4:Â PSO 2.4 continues enhancements to provide speed and reliability to the self-calibration process.
- Particle Swarm Optimization 2.3:Â PSO 2.3 continues enhancements to provide speed and reliability to the self-calibration process.
- Particle Swarm Optimization 2.1: PSO 2.0 introduced the concept of broad solution tree exploration, and with that came the valued added opportunity that a user could monitor this process and manually add and/or remove sites to and from the Analysis Group (AG) with ease. However, users were not yet able to see which solution tree branches have been tried, and which ones worked the best. PSO 2.1 introduces this ability. Along with it, it gives the users the ability to view Boost Factors, Domain Correlation and PSO score for each solution tree branch evaluated.
- Tried Combinations: Users can now access the list of solution tree branches that were evaluated in the self-calibration process. From the Setup screen â View Failed Sites Screen, users can now click on âView All Tried Combinationsâ. When a user clicks on âView All Tried Combinationsâ, a list of each combination, ordered by PSO Score, that was tried during the self-calibration process appears. The list is filterable by Website. Websites and Boost Factor names are ordered alphabetically. Along with the ability to see which combinations bring out the best boost factors, users can select a specific combination by clicking âForce This Combinationâ, and immediately reconfigure the AG.
Note: One of the many PSO 2.1 performance improvements short circuits the PSO process once at least 3 combinations with a sufficient PSO score (this is constantly being updated alongside the PSO score calculations updates described below) and a 100% Domain Correlation are evaluated. Not all combinations are guaranteed to be tried, so a careful inspection of this list may reveal a better combination to try. Market Brew continues to evaluate this algorithm and may elect to broaden or narrow the tree search in the future. - PSO Score Calculations Updated: PSO 2.0 had combinations that scored better without all URL paths matched, simply because they had more sites in the model. PSO 2.1 instructs the self-calibration algorithm that ALL domains and if possible ALL URL paths are matched, at the expense of shrinking the AG, with a minimum # of sites set at 3.
- Market Brew Spotlight 1.0:Â Market Brew Spotlight will bring together a number of new Natural Language Processing (NLP) technologies and a Market Brew Knowledge Graph to provide the user enhanced content abilities within the model. Among other things, Market Brew Spotlight will perform named entity extraction, including entity detection, name resolution, and entity disambiguation.
- Market Brew Knowledge Graph: The Google Knowledge Graph is a knowledge base used by Google and its services to enhance its search engine's results with information gathered from a variety of sources. The information is presented to users in an info box next to the search results. These info boxes were added to Google's search engine in May 2012, starting in the United States, with international expansion by the end of the year. Google has referred to these info boxes, which appear to the right (top on mobile) of search results, as "knowledge panels". The information covered by Google's Knowledge Graph grew quickly after launch, tripling its size within seven months (covering 570 million entities and 18 billion facts). By mid-2016, Google reported that it held 70 billion facts and answered "roughly one-third" of the 100 billion monthly searches they handled. By May 2020, this had grown to 500 billion facts on 5 billion entities.Â
There is no official documentation of how the Google Knowledge Graph is implemented. According to Google, its information is retrieved from many sources, including the CIA World Factbook, Wikidata, and Wikipedia. Market Brew will take a similar approach and use data from these sources to build its own in-house Knowledge Graph. The Market Brew Knowledge Graph will be built using Lazy Initialization, giving the platform the ability to maintain the same precision as Google without having to scale all at once. The Knowledge Graph will be accessible from Spotlight screens, linked whenever a corresponding entity is highlighted. - Market Brew Topics: Using Spotlight, a Market Brew Topic will be created per Webpage. In the future, Market Brew Topics may be broken down into both per-Webpage as well as per-paragraph, to mimic Googleâs Centerpiece Annotation. In addition, a future Topic Focus Score may be created to show users how focused their content is, based on the overall Topic Focus. The Market Brew Topic will be shown on the Spotlight screen for each Webpage.
- Market Brew Topic Clusters: Using the Webpageâs Market Brew Topic and leveraging the new Market Brew Knowledge Graph, the system will provide the user the opportunity to discover new content that should be added to their Website. This content will include a proposed snippet that should be included within the Webpage, as well as anchor text that can be used to link to proposed additional or existing Webpages about these other Market Brew Topics. Market Brew Topic Clusters will be shown on the Spotlight screen for each Webpage, as well as in a dedicated âMissing Topic Clustersâ screen on a per-Website basis.
- Expertise Algorithm (E-A-T): An Expertise algorithm has been created that can score a particular Webpage based on the perceived expertise of the author. Based on the Market Brew Topics, the Market Brew system can collect all of the details from every related entity and compare the writing on that Webpage to the body of content from all related entities. The more coverage that the content has, the higher the Expertise score will be. The Expertise score will be shown on the Spotlight screen for each Webpage, and will be included as a standard Boost Factor.
- Spotlight Focus: After each Webpage is structured using Spotlight, the Market Focus algorithm has been upgraded. Instead of using a keyword density âbag of wordsâ approach to generating initial meaning from a Webpage, the Spotlight results will be used. The incoming anchor text part of the calculation would remain the same, with the final Spotlight Focus Basket being similar to the Market Focus Basket. A Spotlight Focus Score would be generated wherever a Market Focus Score is generated, and used as a new optional Boost Factor. The Spotlight Focus screen will be accessible anywhere the Market Focus screen is currently accessible.
- Particle Swarm Optimization 2.2:Â PSO 2.2 continues to refine some things, notably itâs PSO scoring calculator, some performance optimizations, and some screen optimizations.
- Tried Combinations: The Tried Combinations Screen is now updated. It has more information to make better decisions on which one to pick.
- Self-Calibration Report: The self-calibration report will now show only one row (the row that the PSO process picked). Previously it would show all of the failed attempts before it. Since the last iteration of the PSO process is now selecting which Tried Combination to use, there are no failed attempts before it.
- Adding New Boost Factors:Â some algorithms have been added to the list of Boost Factors that were previously hard-coded and shown on the Webpage Scorecards.
- Added Proxy Servers:Â on the Website Settings screens, users can now enable proxy crawling and select various proxy regions.
- Core Web Vitals:Â We are releasing Core Web Vitals as additional ranking signals to track. We are able to do this at scale (so you can see how your competitors data compares) by injecting the core web vitals scripts on every page that Market Brew crawls.
- Added Similar Words System:Â using neural networks, we are now detecting and injecting similar words in queries. New screens are now available for Resellers to adjust this system, including adding/removing new similar words and adjusting the similarity between those words.
- Added Chrome's Blink Rendering Engine:Â we are now using Chrome's own Blink Rendering Engine, which enables crawling of all JavaScript driven sites.
- Escaped Fragments:Â Market Brew has done a major upgrade in how it crawls escaped fragment sites. Market Brew is now able to handle a site like www.dominos.com, where the page doesnât reload, but various parts do. Market Brew typically throws away fragments in URLs (the â#â and anything to the right of it), as has been the conventional wisdom and guidance from Google for 15 years. The reason is that this part of the URL is never sent to the servers. This part is considered client-side only, but with technologies like ReactJs and Gatsby, these fragments are now driving a large part of the state of a userâs interaction with a website.
There are now a large amount of sites that are using these escaped fragments (the â#!â in the URLs). Because Market Brew has invested into building a state-of-the-art Javascript rendering engine, built upon the popular Selenium open-source project, it was well-positioned to take advantage of the understanding of these escaped fragments. Market Brew will now treat any URLs that have a â!â (exclamation mark) directly after the anchor (#) as a separate page.
âHereâs an example of this in action: https://www.dominos.com/en/pages/order/menu#!/menu/category/viewall/
â
âNotice that you can click on âChickenâ and the page doesnât reload (even though the entire user experience does). In the past, Market Brew would not treat these URLs differently, but now it does. Able to render the page exactly like a user would see in Chrome, Market Brewâs headless Chrome browser brings our rendering investment full circle.
âNote: any sites that are affected by this upgrade will take advantage of these new enhancements immediately after re-crawl. - Particle Swarm Optimization: Market Brew is running a new type of calibration algorithm, currently in shadow mode. Users will not see this, however, over the next few weeks, we will be collecting information on how well the new algorithm performs and will fine tune it before releasing it into the system.
Currently, we use the no duplicate rankings algorithm as the correlation set. This has a nice balance between removing/adding sites, and exposing exact landing pages in the models.
Recently some of our clients have expressed the desire to have more exact landing pages show up. This means that the models would potentially cause more removing/adding sites during the (slower) calibration process. The way to fix this is to have the correlation use the duplicate ranking algorithm, which is a more fine-grained correlation set. It will be more âpickyâ with which sites are in the group, because the constraints will be tighter. The duplicate ranking algorithm is much more processor intensive, as you can imagine, with orders of magnitude more data to compare.
To this end, weâve been working on performance optimization with respect to our Particle Swarm Optimization system. Weâre happy to announce that weâve achieved speedups of 10x over the past few months, and because of this, the ability to try a more intensive optimization algorithm became available. - Workspace Screen Fixes: There were a number of bugs related to the workspace screen filtering and adding/removing of sites. These have been fixed. Weâve also added a few new filters and will look for feedback before adding new features to this screen.
- Lucene Filters: Weâve made some great enhancements to the Lucene Query Parser engine. One situation, where a client was trying to calibrate against the keyword âbalisongâ, surfaced an irregularity that we never saw before.Â
A site that was ranking very well for this keyword, was not showing up at all in our models. www.benchmade.com, as it turns out, had only one type of spelling of this keyword: âbali-songâ. The Standard Tokenizer in Lucene was taking the hyphen and treating it as a delimiter, making the matching of âbalisongâ against âbali songâ impossible (note that it had no problem the other way around, matching âbali songâ to âbalisongâ).
So we introduced Luceneâs Word Delimiter Filter in place of the standard tokenizer. Our early tests are showing a remarkable improvement in these situations. - JavaScript Frameworks: Our JavaScript Chrome rendering engine now supports the following five largest JavaScript frameworks: React, Vue, Angular, Ember, Backbone.js. In addition to the specific support of escaped fragments, which are seen in some of these frameworks, Market Brew is now rendering the snapshot views of these sites at a much higher success rate. A tremendous amount of enhancements have been made in this area, and Market Brew continues to be at the forefront of JavaScript development.
Note again that if you suspect that one or more Analysis Groups are affected by these enhancements, I would highly suggest that you take advantage of the new features as soon as possible.
- Re-Crawl Entire Analyis Group:Â we've added the ability to mass re-crawl an entire Analysis Group. Simply click on the new action in the Actions dropdown.
- Anchor Text Distribution:Â We have greatly enhanced our keyword research tools. To select the Anchor Text Distribution screen, click the link in the data dropdown button underneath the site you wish to research. Every word in every anchor text in the site is evaluated and associated with a specific amount of link flow. We call this âAssociated Link Flow Shareâ. This is the relative amount of ranking power that each link transmits to a target page. Some links are more important than others, and this metric gives us that meaning. Click on the âShow Competitorsâ checkbox and you instantly switch from the target siteâs keywords to itâs competitorâs keywords. Any site that appears alongside the target site, in any Analysis Group, is included. Therefore, the more Analysis Groups the better the keyword research becomes.
- Link Flow Finder: As you know, one of the most important features of Market Brew is the Link Flow Distribution analysis. We've had a lot of success stories from brands utilizing the Link Flow Distribution analysis to boost traffic to large portions of their sites, but this process has been far from automated. One of the biggest hurdles for this that we've seen is having the knowledge on the team to know where to strategically add Link Flow to certain pages in a site. With our new Link Flow Finder feature, this hurdle should be a thing of the past.
The Link Flow Finder works like this: for each target page, the system takes the already calculated Market Focus Basket of phrases assigned to that URL, and uses those phrases to do a proximity search on all the other pages in the site. Each resulting text fragment / snippet, with these key phrases highlighted, is then presented to the user with the corresponding page that it is on. Some Market Brew magic happens when our models find that the target siteâs Market Focus Basket is NOT the best Market Focus Basket. When this occurs, it is the outperformer site that is used to harvest the keywords to search against. This is particularly helpful when a target site doesnât know what the correct keywords are yet. Therefore, the more Analysis Groups the better the Link Flow Finder becomes.
The user only needs to click "Add Link Flow" under any page in the Link Flow Distribution screen, and then add links to the target page using the highlighted snippets. The snippets are even ordered by the most potential Net Link Flow Share, making this process a very powerful approach to shaping the Link Flow Distribution and Balance. - Domain Rank Finder: Another huge enhancement in the model is our new Domain Rank guidance. The Domain Rank Finder works like this: backlink sites that link to two or more of the target site's "competitors" but NOT to the target site itself, are suggested as potential link partner sites. What is unique about the way we do this is that we use the other sites that accompany the target site in each Analysis Group as the "competitor" list. This allows us to pick sites that sometimes are not a direct competitor (and therefore more likely for a link from the same source to be easier to acquire). Therefore, the more Analysis Groups the better the Domain Rank Finder becomes. These potential links are ordered by "exclusions" first (how many "competitor" sites get links from these sites) and then they are sorted by the Net Link Flow Share that a new link on that site would provide (how powerful the backlinks on that page are).
- Updates to Existing Reports:Â The Market Brew Conversation report is now generated immediately after Analysis Group setup! No need to re-crawl each site at least twice before generating the report. This will further automate the process of prospecting, and for our A La Carte customers, it will generate a link to the report immediately upon purchasing the product. All trend analysis on the Market Brew Conversation report is removed for the first report (as there is only one snapshot of data at this point). All competitor âBiggest Weaknessâ and âTrend Analysisâ sections have been removed: the Conversation is solely focused on the target site now, resulting in more focused and less noisy content. Both the Link Flow Finder and the Domain Rank Finder recommendations will also be listed on the Simulations screens as well as the automated Conversation reports, when applicable. You should see these start to show up as your sites are re-crawled and new reports are generated. We believe that these two improvements to the Market Brew product make it both incredibly powerful and easier to use. We are constantly striving towards full automation and these enhancements make good on that promise. In addition to the two major enhancements mentioned above, we have added detailed analysis of the HTML scoring, including featured text fragments, giving users transparency into the underlying Lucene Query Parser scoring. We have also added detailed analysis of the URL Host and URL Path much in the same way we show the META Title analysis, complete with highlights and recommendations. As you will see, there have been some major cosmetic upgrades to both the Simulations screen and the Conversation report, and improvements in rendering on both mobile and desktop browsers.
- Additional Rank Tracker Databases:Â We have added additional databases that have become available from SEMRushâs API for Analysis Group setup. In addition, we have added the country name to the dropdown list, before we were only specifying country code.
- Updated Chrome JavaScript Engine:Â we have updated the JavaScript parsing engine to the latest stable version of headless Chrome (Google Chrome 88.0.4324.182). Upgraded rendering as well as new Web Core Vitals scripting are the biggest features, with internal performance enhancements as well.
- Two different account types now available: Both per-crawl and per-Analysis Group crediting are now available to Resellers.
Previous release notes from 2006-2020 have been archived and are available on request.
