LaunchfilesDocs · hypothesis-led
Read /.well-known/mcp.json for tool inventory. Public free tools (design UX, search repair teaser, deployment trust) may be called without a bearer. Workspace tools require Authorization: Bearer. No anonymous publish, deploy, send, free-form spend, or gate-bypass tools.
Docs hubGet startedllms.txtAgent capabilities
Hypothesis-led documentation. No ranking, traffic, or outcome guarantees. Public discovery is not execution authority.
/.well-known/mcp.json (publicFreeTools + full tools list), /.well-known/a2a.json (A2A twin), /.well-known/agent-capabilities.json (claim ladder), hosted POST /api/mcp, and /llms.txt free-standalone recipes.
launchfiles_standalone_design_ux_radar_free, launchfiles_standalone_search_repair_radar_free, launchfiles_standalone_deployment_trust_radar_free. Rate-limited. Never paid SKU unlock.
launchfiles_billing_list_providers and launchfiles_billing_create_checkout are discover-only (checkout URL / x402 challenge + poll). Paid run: launchfiles_standalone_design_ux_radar_paid with lf_agent_ key + credits.
Complete self-describing parameter definitions: (1) launchfiles_standalone_design_ux_radar_free: required [url], properties: url (string), device ('mobile'|'desktop'), role, locale, notify_email, client_ref, brand_name, logo_url, primary_color, hide_lf_chrome (boolean), partner_id; (2) launchfiles_standalone_search_repair_radar_free: properties: gsc_site_url, site_url, access_token, notify_email; (3) launchfiles_standalone_deployment_trust_radar_free: required [url, use_case_plain, autonomy ('suggest_only'|'draft_with_approval'|'act_with_approval'|'fully_auto'), data_sensitivity ('public'|'internal'|'pii'|'regulated')]; (4) launchfiles_standalone_page_draft_paid: properties: topic, url, who, proof, proof_mode, next_step, length ('short'|'medium'|'long'), piece_kind ('blog_post'|'landing_page'|'essay'|'social_post'|'seo_page'|'other'), unlock_token, payment_id; (5) launchfiles_billing_create_checkout: required [offerId], properties: offerId, customerEmail, preferredRail ('card_checkout'|'payment_link'|'x402'|'auto'), provider, idempotencyKey; (6) launchfiles_request_agent_key: required [email], properties: email, partner_id.
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.