LaunchfilesDocs · 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 /cursor-rules-vs-work-orders. This docs page is the contract-oriented definition.
Launchfiles executes this through bounded work orders, deterministic pre-commit gates, dual-ledger verification, and cryptographic approval receipts. Rather than generating unverified audit essays or soft-green theater, autonomous agents operate inside strict byte-range boundaries with verifiable unit economics, human review gates, and deterministic regression guarantees across every production change.
| Dimension | Unbounded AI Chat / Audit Essays | Launchfiles Bounded Work Orders & Receipts |
|---|---|---|
| Execution Scope | Unbounded chat, hallucinated advice, unverified file rewrites | Bounded AST patches via work orders and pre-commit gates |
| Verification & Proof | Soft-green claims without receipts or regression checks | Dual-ledger verification with cryptographic receipts |
| Opportunity Discovery | Invented keywords and unranked suggestions | Statistical triage via Search Repair Radar |
| Economic Model | Opaque token burn with zero outcome guarantee | Transparent pricing with strict byte-range safety locks |
Next safe action
Prefer receipts over claims. Prefer fail-closed honesty over impressive incompleteness.