UNIVERSITY · LESSON 8 · RUNNING IT · 4 MIN READ

Keeping agent readiness from regressing

Readiness is a property of this week's release, not a project you finish.


Agent Readiness Compare editors · Spec status checked September 2026

Answer

Agent readiness breaks quietly: a redesign moves pricing into a client-side widget, a new bot rule blocks an assistant, a login change adds a challenge. Put file checks in CI, re-run key tasks after releases that touch pricing, sign-in, bot rules or checkout, keep a dated log, and watch the standards for changes.

On this page
  1. 1. What usually breaks?
  2. 2. How do you catch breaks before agents do?
  3. 3. When should you re-run task tests?
  4. 4. How do changes in the standards affect you?
  5. 5. How do you tell a site change from a method change?

1.What usually breaks?

  • Rendering: a page rebuilt as a client-side app returns an empty shell to agents that do not run JavaScript.
  • Access: a new CDN or firewall rule blocks a crawler or agent that robots.txt allows.
  • Links: llms.txt still points to pages that moved.
  • Forms: a redesigned form loses its labels or adds a custom control.
  • Challenges: a bot challenge appears on a step an agent used to pass.

Each maps to a check in the checklist, so the fix is known. The hard part is noticing.

2.How do you catch breaks before agents do?

Run file checks on every deploy. A CLI makes this practical: ora.ai documents npx ax audit for scoring a URL from a terminal or CI job, and its MCP server can rescan after each fix. Scripted requests work too: fetch the pricing page and assert that the plan names are in the HTML, fetch /llms.txt and assert that every link returns 200, and request a key page with Accept: text/markdown and check the content type.

3.When should you re-run task tests?

After any release that touches pricing, sign-in, bot rules or checkout (checklist L5.5), and on a fixed schedule otherwise. Keep the same tasks and the same expected answers so runs can be compared, and date every entry in the log.

4.How do changes in the standards affect you?

The standards moved several times in 2026: A2A reached v1.0.0 on 12 March, the MCP specification of 28 July made the protocol stateless, and llms.txt was revised to v2 in August. A change can make a working setup outdated, such as an MCP server that relies on sessions, or add something worth adopting, such as llms.txt link relations. Our news page lists these releases with dates and sources.

5.How do you tell a site change from a method change?

When a score moves, check two things: what you shipped since the last scan, and whether the scanner changed its checks. ora.ai's Deep Scan v2 in July 2026 is an example of a method change: it derives its checklist from agents run on real tasks. Recording the date and the method with each score makes the cause clear.

Next: setting a policy for AI crawlers and agents.

Source: ora.ai llms.txt · ora.ai docs · ora.ai, Deep Scan v2 · A2A releases · MCP blog, The 2026-07-28 specification · llms.txt changes · Reviewed Sep 2026

Back to University