Skip to content

Playbook

Review a design

Paste the design. Score it against named failures and the five readiness questions.

When: A design doc, a PR that adds an agent, or a framework pitch.

  1. 01

    Run the reviewer

    Paste into /review or POST /api/canon/review. Do not review by vibe.

    The Named Failures
  2. 02

    The five questions

    Termination, sandbox, context builder, eval set, pause API. Missing is a block, not a nit.

    Anti-Patterns
  3. 03

    Load the fix

    Each hit points at a playbook. Follow that, do not add a crew.

    Start Simple

Done when

  • Every hit has a named failure and a next article. Ready-to-build is either green or a ticket.

Refuse

  • Eval by demo. 20–50 real tasks before the framework. promptfoo, Inspect, DSPy. CI on prompt change.
  • Unbounded loop. Force a done schema, a step cap, and a money cap. 'Done' is a tool or a structured intent.
  • Unsandboxed exec. E2B, a container, OpenHands isolation, or a policy sandbox. Secrets stay in the executor.
  • Star-driven selection. Pick for the constraint: checkpoints, types, harness, documents. Read Canon's atlas.