LaunchfilesDocs · hypothesis-led
A scoped challenge token can create temporary prod_program_suite_* products, run missions, retrieve results, and delete the temporary product. It cannot publish, deploy, spend, or access real customer products outside the challenge prefix.
Docs hubGet startedllms.txtAgent capabilities
Hypothesis-led documentation. No ranking, traffic, or outcome guarantees. Public discovery is not execution authority.
Use /quickstart for the founder-readable loop: manifest → product → mission → poll → artifact → receipt → cleanup.
Authenticate to /api/founder/prod-challenge-manifest with the founder-provided token. Follow the manifest endpoints only.
Send the developer key as Authorization: Bearer (hosted MCP also accepts the same developer key on x-api-key or JSON-RPC _meta). On /api/founder/* it runs challenge products and missions; on hosted MCP and A2A a verified developer key is the developer tier and unlocks Writer-short and paid Page Draft without Stripe. If hosted Cursor MCP tools/call does not forward the connector developer key, use A2A page_draft.run_short at POST https://launchfiles.app/api/a2a with Authorization: Bearer and the developer key — that door already works. unlock_token accepts only pdr_unlock_* from a settled checkout — a developer key there fails with UNLOCK_TOKEN_IS_CHALLENGE_TOKEN. A PROD_CHALLENGE_TOKEN_INVALID answer carries token_diagnosis (signature_mismatch, expired, malformed) so you can fix the paste or mint again. Without a verified bearer, hosted MCP tools/list shows the public list only. An expired token stays on that public list and returns MCP_AUTH_INVALID with next_action to mint again (POST /api/founder/prod-challenge-token or Today). Cursor shows launchfiles_keyword_planner_research and launchfiles_hunt_gap_scan only after a verified developer key, registered lf_agent_ key, or hosted MCP token.
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.