Sample report
Exactly what lands in your inbox.
Ungated. Sample data for a fictional travel site (northwind-travel.example): the layout, evidence and wording are what customers receive.
Release 4.18 · Book 2 nights · 60 cells · 24 Sep 2026
Northwind Travel
NO-GO
2 open P0 findings
sample · book.northwind-travel.exampleSample data
| Persona ↓ / Agent → | Claude CU | Gemini CU | Browser Use | OpenAI CUA | Stagehand |
|---|---|---|---|---|---|
| First-timer, mobilepatience 5 · iPhone | |||||
| Impatient shopperpatience 2 | |||||
| Older adult, low dexteritymin target 44px | |||||
| Non-native reader (B1)CEFR B1 | |||||
| Keyboard-onlyno pointer |
Column fails → agent-class problemRow fails → persona problemSame step in ≥3 cells → product bug
Click any cell to see the blocking step and evidence.
Top Confirmed findings
| Finding | Sev | Cells | Human |
|---|---|---|---|
| Consent checkbox has no accessible name and renders below the fold | P0 | 14 | Confirmed |
| Date-picker traps keyboard focus; Escape does not close it | P0 | 6 | Confirmed |
| Bot management returns 403 to Gemini computer use on /checkout | P1 | 5 | n/a |
Narrated repro
“I’ve filled everything in. The Continue button is grey and nothing tells me why…” (AI-generated narration over the real recording.)
What an Alt Matrix does not prove.
Personas are simulations, not people. Findings are evidence of behaviour we observed on a given date with a given model version. They are never a statement that a site is “compliant”, “certified” or “agent-ready”. Consumer-agent classes are behavioural approximations, not the named products. Every published precision figure states its sample size and confidence interval. Read the full limitations statement →
Want this for your funnel?
Run one free cell on a property you own. No sales call, no card.