Docs · hypothesis-led

Launchfiles documentation

Launchfiles is the launch operator for AI-built products: it takes a product to its first paying customers and keeps them, through agents acting inside a policy you approve, with a receipt for every public act. This docs hub explains the objects and mission types. It is not an autonomous page builder and does not grant execution authority.

Try a bounded mission Read agent contract

Get started llms.txt Agent capabilities

Hypothesis-led documentation. No ranking, traffic, or outcome guarantees. Public discovery is not execution authority.

What this hub is for

Founders and external agents need a stable map of what Launchfiles does, what it refuses, and which surfaces are educational vs executable. These pages are labeled hypotheses: they teach category and contracts without inventing demand volume.

Start here

Humans: read the operating loop, then mission types, then try a bounded mission on Quickstart. Agents/LLMs: read Agents, MCP, Authorization, and the public discovery files (/llms.txt, /.well-known/*). Public discovery is metadata only.

Claim ceiling

Hypothesis-led documentation. No ranking, traffic, or outcome guarantees. Public discovery is not execution authority.

How does Launchfiles documentation work in an agent-first engineering harness?

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

Learn the contract, then run a bounded mission.

Prefer receipts over claims. Prefer fail-closed honesty over impressive incompleteness.

Quickstart