Skip to the content
AI Test AutomationPreview AI Security Learning Center

AI Test AutomationLearnPrinciple to test

Principle to test Preview

“Make the AI safe” is not a test. Here is how to write one.

One chain from the need to the evidence, worked through for six principles of agent security, each ending in tests you can run and evidence an auditor can read.

Five roles, one requirement

Everyone asks for the same thing in different words

"We need the AI to be safe" is a fine goal and an impossible test. Business, engineering, risk, compliance and audit each describe the same problem in their own words, and a requirement is only ready when it answers all of them: one chain from the need to the evidence, with a test in the middle and a person at the end.

Business

Get this approved, faster.

A requirement that is ready the first time does not bounce back.

NeedOwner

Engineering

Tell me exactly what to test.

Acceptance criteria a test can check, and the test itself.

Acceptance criteriaTest

Risk

What risk is left?

The policy it answers, and what the tests do not prove.

Risk or policyWhat is left

Compliance

Show me the requirement was met.

The requirement, tied to a passing test.

RequirementTest

Audit

Show me the evidence.

What is kept, where, and who answers for it.

EvidenceOwner

The chain

From the need to the evidence, in seven links

Each link answers one of the five roles. Skip one, and somebody's question has no answer when it matters.

  1. Need

    The business need or the problem, in one sentence.

  2. Risk or policy

    The law, standard or policy behind it, with a link.

  3. Requirement

    What the product must do, specific enough to build.

  4. Acceptance criteria

    The conditions that mean it works, written so a test can check them.

  5. Test

    How we verify it, automated and repeated.

  6. Evidence

    What is kept, and where, to show it happened.

  7. Owner

    The person or role who answers for it.

Worked through

Six principles, written down to the test

Pick one. Each runs the whole chain, with the real incidents behind it, tests you can run from the home page, and an honest definition of ready: a criterion with no test yet says so. Copy any of them as a ticket for your backlog, or download it with its tests.

Principle

High-risk agent actions require human oversight.

  1. 1

    Need

    Agents can delete data, deploy changes and move money. A mistake, or a hijacked agent, should not be able to do that unchecked.

  2. 2

    Risk or policy

  3. 3

    Requirement

    High-risk actions, as the policy lists them, run only after a named person approves that specific action.

    Epic: Approval for high-risk agent actions
    Story: As the risk owner, I want high-risk actions held until a person approves them, so that nothing consequential runs unreviewed.

  4. 4

    Acceptance criteria

  5. 5
  6. 6

    Evidence

    • The approval log: each high-risk action, who approved it, when, and the outcome.
    • The CI report of the approval tests, kept with each release.
  7. 7

    Owner

    The risk owner approves the list of high-risk actions; the platform team owns the gate and its tests.

About the law in these chains

The EU AI Act's rules for high-risk AI systems, among them Articles 12 (logs), 14 (human oversight), 15 (cybersecurity), 19 (providers keep the logs) and 26 (deployers), apply from 2 December 2027 for the uses listed in Annex III and from 2 August 2028 for AI in the products of Annex I. The Digital Omnibus on AI (Regulation (EU) 2026/1744, in force since 27 July 2026) moved them from 2 August 2026 and 2 August 2027 respectively. Whether an agent is high-risk depends on Article 6 and those annexes, so for most agents these articles are a reference rather than a duty. The Act does not use the words prompt injection, egress or MCP, and it mentions secrets only as trade secrets; where a principle links to Article 15, that is our reading.

Sources: EUR-Lex: Regulation (EU) 2026/1744, the Digital Omnibus on AI · European Parliament Legislative Train: Digital Omnibus on AI · European Commission: the AI Act and its timeline

Definition of ready

Is your requirement ready? Paste it and see

Three questions before anything is built. The check below runs in this page, nothing is sent anywhere, and it is strict on purpose: words like "safe" or "secure" cannot be tested.

  • Can engineering build it? There is a specific requirement with at least one acceptance criterion, not just words like safe or secure.
  • Can we test it? Every acceptance criterion has a test that can pass or fail.
  • Can we prove it happened? The evidence to keep is named, and so is its owner.

If any answer is no, the requirement goes back to its owner. That is the definition of ready.

The verdict appears here.