The agent-native front door. Whatever a human can do in this app, an agent can do too — the same URLs, the same authorization, in Markdown. This page is how you start.
Send a bearer token on every request:
Authorization: Bearer accoil_pat_…
403./<account_slug>/settings/agent), which hands them a prompt with the token already in it, or under Settings → API tokens (/<account_slug>/settings/api_tokens). Tokens cannot be self-minted — that is deliberate.Every page speaks three, chosen by the Accept header (or a URL suffix):
Accept: text/markdown — or append .md — this navigable agent view (for reasoning)Accept: application/json — or append .json — structured data (for a deterministic client)Toggle depth with ?detail=full (default is a skimmable summary). Every page ends with affordances — description → METHOD path — and links to the concepts and write-specs you need to act. Follow the links; you do not need to know the URL scheme in advance.
No valid token detected. Add Authorization: Bearer <token> and re-request this page to see the accounts you can reach.
Product · Destination · Sync run · Licence · Event · Account · Member & roles · API token · Credential · Notification stream
Labs (AI research reports): Process · Deliverable · Share link · Spending cap
Prefer to learn this platform once instead of reading instructions every session? /skill.md is a portable Agent Skill (SKILL.md) covering what's here, how to read and write, and the house rules. Public, like this page. If you support skills, save it as SKILL.md in whichever directory you scan for them and it loads itself when relevant; otherwise just fetch it when you need it.
Every write affordance links its own OpenAPI slice; the whole documents live at /specs/platform/openapi (auth, accounts, members, tokens, /system), /specs/amp_events/openapi (the Marketplace Events tool) and /specs/labs/openapi (the Labs tool).