Methodology
The method behind AI agent test runs. The automatic site check is described on our checker page.
Updated
Find waterproof trail shoes under $150, then the delivery cost.
Example runA readiness signal combines discoverability, successful task completion, repeatability and efficiency.
A missing agent-native surface cannot erase a successful browser result, and the reverse is also true.
Crawl access, citation surfaces, content consistency and machine-readable context.
AI crawlers our checker reads your robots.txt for
Pick a crawler to see which rule applies
User-agent: GPTBotDisallow: / User-agent: ClaudeBotAllow: / User-agent: Google-ExtendedDisallow: /checkout User-agent: *Allow: /
Page
Rendered interaction, semantic controls, keyboard path, sessions and responsive behavior.
Declared surfaces are noted when we detect them. Running their tools is coming later.
Stop gate. The agent stops here: no cart, no login, no payment.
Prompt wording alone never defines success. The contract states the goal, permissions, stop gate and assertions.
Literal checks
AI check
The AI check can't turn a failed check into a pass.
A run succeeds only when literal checks confirm the intended final state. An AI check then reads the same evidence and can confirm the result or flag it for review. It never turns a failed check into a success, results it checked are marked AI-checked, and concierge results are also reviewed by Aiscovery.
Session evidence explains whether a nominal success was fast, stable, repeatable and autonomous.
1 / 5
Opened the home page
Time per step
Each page the agent visits gets a bounded Cumulative Layout Shift measurement in our browser. It is a lab value, not field data. Movement of the target around each click is not measured yet.
Layout shift on this page
0.00
Each test run is one attempt by one named agent, and we plan up to three attempts per agent for each key task. The agent, model, viewport, locale and safety rules stay attached to every run.
Results separate website, agent and platform failures.
Verdict
What happened on the tasks we tested.
Severity
Critical blocks a key task or creates a real safety risk.
High creates major repeatable friction or unreliable completion.
The verdict and its confidence are reported separately.
The verdict reflects what we tested. Confidence reflects coverage, attempts, evidence quality and open questions. Neither becomes a single score.
Verdict
Partial
Confidence
Medium
Artifacts are stored with stable IDs, timestamps, environment and retention rules.
llms.txt, llms-full.txt, robots.txt and declared agent surfaces such as WebMCP forms are detected (declared) and lifecycle-labeled when our checker sees them. We don't run MCP, OpenAPI or WebMCP tools yet, and their absence is not a failure.
What our checker found on the example store
Detected tools are not run yet.
Agent products, policies and models change. Results are versioned observations from a defined environment, not permanent compatibility guarantees.
Start with a scoped audit and keep every conclusion connected to evidence.