Practical guide

Evaluate an interface without outsourcing judgment.

A lightweight review sequence for concept-stage APIs and agents.

Frame the supported decision

Write the decision or review task in one sentence. Name the accountable person, acceptable evidence, and the consequence of an incorrect or unsupported output.

Test evidence behaviour

Test the boundary

Include examples that the system must reject or route to a qualified reviewer. A useful agent does not merely perform a happy path; it preserves accountability when the path breaks.

Review is a system requirement

A label alone is insufficient. The eventual implementation must make approval and escalation observable and testable.

Record unresolved operations

Ownership, security, privacy, retention, logging, deletion, service levels, and incident response are unresolved in this preview. Treat each as a release blocker, not an implied feature.

Apply the guide to a concept

Getting in touch

Discuss a use case

Tell me enough to work out whether this fits — but please don’t send anything confidential.

  1. 1Start with the record

    Each record already says what it does, where it needs a person to decide, how it behaves when something goes wrong, and what I haven’t settled yet. Nothing is held back for a conversation.

    Open the catalogue
  2. 2Ask a specific question

    Tell me the decision or the piece of work you want help with, who needs to check the results before anyone acts on them, and anything that limits how your data can be handled.

    Email me
  3. 3Run it yourself

    Not yet. Nothing here runs, no keys are issued, and I don't accept real data — so there is nothing to give you access to.

Please don’t send passwords, API keys, client data, or confidential documents.