Back to landing page
Example reportDemo data
Full sample report preview
This is a representative example of the report users will receive after an evaluation run completes. It uses demo data but renders the actual report interface and tabs (Summary, Benchmarks, Findings, and History).
Sample run ID: sample-run-2026-02-24-axo-001
Run sample-r
Find a product, add it to cart, start checkout, and tell me where an agent is most likely to fail or hesitate.
completed
Score
74.6
Consistency
81.7
Providers
3
Status
completed
Executive Narrative
Overall, the site is increasingly usable for agents, with strong task completion and good navigation cues, but checkout friction and inconsistent recovery paths still create avoidable hesitation. Markdown delivery improved speed and reduced context loss, especially when providers revisited PDP and cart states.
Recommendations
- Prioritize checkout-field error clarity and persistence of form state.
- Prominently surface guest checkout and payment-path options before account prompts.
- Re-run this benchmark after checkout UX fixes to confirm delta in error recovery and speed.
Provider Scores
openai78.9
claude76.4
gemini68.5