GEO Testing
Tools
GEO Testing helps you measure the real impact of your SEO and content changes on AI visibility. Instead of guessing whether your optimizations made a difference, run structured experiments and see the data. Available on Scale plans and above.
What it does
- Runs time-based tests that compare the same URL group's performance before and after a change date
- Runs split tests that compare a test group against a control group for more reliable results
- Tracks citations (how often your URLs appear as AI sources) and unique cited URLs per group
- Provides 6 analysis tabs: Overview, By AI Model, By Prompt, Top Sources, AI Traffic, and AI Analysis
- Generates AI-powered analysis that interprets your test results and provides actionable insights
- Automatically creates annotations on change dates for visual correlation on charts
How to use it
- Navigate to GEO Testing in the sidebar (under Tools)
- Create URL Groups first — named collections of URLs you want to track as a cohort
- Add URLs to each group (paste one per line, up to 100 at a time)
- Click New Test and choose your test type:
- Time-based: select one URL group + a change date. LLM Pulse compares before vs. after
- Split test: select a test group + a control group. External factors affect both equally, giving you a cleaner signal
- Monitor results across the 6 tabs as data accumulates
- Use the AI Analysis tab to get an AI-generated interpretation of your results
URL Groups
URL Groups are the foundation of GEO Testing. A URL group is simply a named collection of URLs that you want to track together.
- Give each group a name, optional description, and optional color for chart identification
- LLM Pulse automatically normalizes URLs (removes tracking parameters, trailing slashes) and deduplicates
- For split tests, make your test and control groups as similar as possible (same template, similar traffic levels)
- You can create as many groups as you need
Tips & notes
- Available on Scale plans and above
- Time-based tests are best for: title tag changes, meta description updates, content rewrites, schema markup additions
- Split tests are best for: large-scale template changes, new content strategies, structural site changes
- Annotations are created automatically when you set a change date, making it easy to correlate changes with performance shifts
- The AI Analysis feature uses your actual test data to generate insights — it's not generic advice
- Results improve with more data points, so let tests run for at least 2-3 weeks before drawing conclusions