UNIVERSITY · LESSON 6 · CHOOSING TOOLS · 4 MIN READ
File checks and task runs: two ways to test agent readiness
One tells you the signals are present; the other tells you whether an agent got through.
Agent Readiness Compare editors · Spec status checked September 2026
Answer
A file check confirms that something exists: robots.txt returns 200, llms.txt has an H1, a page answers Accept: text/markdown. A task run sends an agent to do something, such as find a price or reach a demo request, and records where it stopped. You need both: file checks are fast and repeatable, and task runs show whether the signals add up to a finished job.
On this page
1.What does a file check test?
A file check makes one request and inspects the response. Typical examples from our checklist: robots.txt returns HTTP 200 and parses (L1.1), /llms.txt exists with an H1 and working links (L2.2), a page returns markdown when asked (L2.3), /.well-known/agents.json returns JSON (L3.3), and an unpaid request to a paid endpoint returns HTTP 402 (L4.3). Each has a clear pass or fail, which makes file checks cheap enough to run on every release.
2.What does a task run test?
A task run gives an agent an intent, such as finding the price of a team plan, and follows it through the site. ora.ai Journey is built for this: it points a real agent at a page and records "what it found, where it stalled, whether it finished." Task runs catch failures no single file check sees: a price that is in the HTML but hidden behind a toggle, a sign-up form whose fields have no labels, or a bot challenge on the last step (checklist L2.5, L3.2 and L4.2).
3.Why do the two sometimes disagree?
Because a task depends on several layers at once. A site can pass every discovery and reading check and still fail the task because the demo form needs a custom gesture. The reverse happens too: an agent can sometimes finish a task on a site without an llms.txt, because the pages themselves are readable. Treat a disagreement as information: it points at the step where the signals and the journey part ways.
4.Which tasks should you run?
- Can an agent find and accurately explain our pricing?
- Can it recommend the right plan for a stated requirement?
- Can it find the documentation page that answers a buyer's question?
- Can it complete a demo request or the next step we care about?
These are the four questions on agent readiness and AEO. Keep the list short and the same from run to run, so results can be compared.
5.How often should you run each?
File checks belong in CI or a scheduled job; ora.ai's npx ax audit is one way to run them from code. Task runs take longer and vary more between runs, so run them after releases that touch pricing, sign-in, bot rules or checkout (checklist L5.5), and keep a dated log.
Next track: how to run your first agent task test.
Source: journey.ora.ai · ora.ai llms.txt · RFC 9309 · llmstxt.org · agents.json repository · x402.org · Reviewed Sep 2026