Is your website ready for AI agents?
Compass tests whether AI agents can complete real tasks on your site — finding the navigation, extraction, and citation failures that traditional SEO crawlers miss.
Crawlers map URLs. Agents complete tasks.
Traditional SEO tools tell you whether a page can be reached. Compass tells you whether an AI agent can actually get there, understand it, and use it to answer a real question.
What Compass gives you
A complete picture of how AI agents experience your site — not just what they can crawl.
AI agent task simulation
Run 140+ pre-built tasks that mirror how ChatGPT, Claude, Perplexity and Gemini actually navigate your site — not just how they crawl it.
Navigation path analysis
See the exact routes AI agents take, where they get stuck, how many steps they need, and whether they reach the page that should answer the query.
Actionable failure reports
Get prioritised fixes for discovery, navigation, extraction, and action failures — tied directly to the pages and links that cause them.
How it works
Set up a project, run the audit, and get a prioritised fix list.
Add your site
Connect a domain, choose a project, and set the scope. Compass builds a task graph from real search and agent behaviours.
Run the audit
Pick a task set — or build your own — and run the audit. Compass simulates AI agents completing journeys across your site.
Fix what matters
Review the failure report, export the fixes, and track changes over time. Rerun audits to confirm agents can now complete the task.
What Compass measures that crawlers do not
Most tools stop at the page level. Compass models the full agent journey.
| Task completion rate | Whether users can find what they need | UX Researcher |
| Navigation path length | Where the journey breaks down | CRO Team |
| Failure type by page | What’s blocking progress | SEO Specialist |
| Agent compatibility | Whether all users can reach content | Accessibility Engineer |
The failure modes Compass finds
Every failed task falls into one of these layers. Fix the right layer and the agent journey succeeds.
Discovery failures
AI agents cannot reach the page at all — robots.txt blocks, orphan pages, or index gaps.
Navigation failures
The agent reaches the site but cannot find the right page within a reasonable journey.
Extraction failures
The right page exists, but the agent cannot extract a clear, citable answer.
Action failures
The agent finds the answer but cannot complete the intended next step (trial, demo, purchase).
Loop-prone structures
Menus, breadcrumbs, or facets send agents in circles instead of toward the answer.
Hallucination triggers
Thin, ambiguous, or contradictory content causes the agent to cite the wrong page or skip you entirely.
Four teams, one dataset
Compass turns the same AI navigation audit into answers for different disciplines.
UX Research
Map how users actually navigate your site — at scale. Run 140+ navigation scenarios automatically and see where tasks complete, loop, or fail.
UX Research
The problem
Traditional UX research is expensive and small-sample. You can’t manually test every task on every page for every user segment.
What Compass measures
A SaaS audit found “Find pricing” completed in 2 steps, while “Cancel subscription” needed 7 clicks and a support form. That’s the kind of insight a survey won’t give you.
Accessibility
The problem
Automated accessibility scanners test individual pages. They don’t tell you whether a screen-reader user can actually find a button from the homepage.
What Compass measures
A page can pass axe but still be six navigation steps from the homepage with no semantic link labels. Compass finds the journeys WCAG can’t see.
Conversion Optimisation
The problem
Analytics shows the symptom: drop-off at step 3. Compass shows the cause: a dead-end link, missing nav path, or CTA hidden behind a hover state.
What Compass measures
“Find the returns policy” failed on 3 of 5 e-commerce sites — the policy was buried under a hover-only mega-menu. Fixing the navigation took 2 hours. No A/B test needed.
Technical SEO
The problem
A page can be indexed, canonicalised, and technically perfect — but if an AI agent can’t navigate to it, it’s invisible to the users who matter.
What Compass measures
Compass complements Screaming Frog and Search Console by answering not “Can this page be reached?” but “Can an AI agent complete a task starting from the homepage?”
Start finding the failures that matter
Run your first AI navigation audit and see exactly where agents get stuck on your site.