Writ

Platforms get API traffic from AI agents trying to do real economic actions — refill an account, top up credits, place an order — and block it as fraud, because nothing answers "who committed this action?" for an agent. Writ resolves any action to its chain of agency: action ← agent (Ed25519 keypair + runtime metadata) ← mandate (scope, spend caps, expiry — revocable live) ← KYC'd principal ← liability. Platforms integrate one middleware (requireKYA) and get allow/deny decisions plus signed, tamper-evident records; agents carry the passport via SDK or MCP server. Records, not rails: no custody, no tokens, rails-neutral (x402 / AP2 / agentic-checkout interop). Live now: a demo brokerage where an anonymous agent gets 403'd into onboarding, a passported agent refills under a $2,500/week mandate, the cap denies at the boundary, and revocation lands on the next call — 11/11 acceptance checks green against production. Self-serve since 2026-08-18: sign up at api.writhq.com/signup in three fields and you get an account, a working key, and a console — free for 1,000 verifications a month, $99/mo for 100,000, self-serve upgrade through Stripe. Log in to manage named API keys (one per service, each revocable on its own), read the immutable decision log, and set your agents' permissions: the mandate form spells out what an agent may do, up to what caps, at which platforms, until when — and revoking lands on its very next action. Quotas are a billing limit and never a verification decision: over-quota returns a 429 that deliberately carries no decision field, so an unpaid invoice can never look like an agent lacking authority.