Docs · hypothesis-led
A work order is the atomic unit of agent or human work: allowed scope, forbidden actions, expected outputs, and acceptance evidence. It is narrower than a chat prompt and is required before serious execution is credited.
Docs hubGet startedllms.txtAgent capabilities
Hypothesis-led documentation. No ranking, traffic, or outcome guarantees. Public discovery is not execution authority.
Owner, capability or role, product/workspace scope, expected outputs, forbidden actions, and idempotency where retries exist.
Not a free-form prompt. Not a green “done” without a receipt. Not permission to publish, deploy, send, or spend unless approval grants that exact scope.
For a founder-facing explainer with the same job, see /ai-work-orders. This docs page is the contract-oriented definition.
Next safe action
Prefer receipts over claims. Prefer fail-closed honesty over impressive incompleteness.
