127 workers. One door.

A public map of a working AI operations estate - what it takes to let an assistant actually run a business.

127 live edge workers
36 integrations
9 Postgres databases
9 vector indexes
5 edge SQL databases
1 entryway
14 capability domains
verified 2026-09-13

Every AI client - Claude, ChatGPT, Perplexity, anything that speaks MCP - comes in through a single scoped door. That door holds almost no logic. It authenticates the caller, decides what that caller is allowed to touch, and forwards the request to the one worker that owns the job.

Everything past the door is small and single-purpose. That is the point: a capability you can name is a capability you can verify, monitor, and turn off. The one remaining monolith is labelled as such, and is being retired on purpose.

What it plugs into

The workers are the easy half. The fleet does not live on an island - it talks to 36 external systems, and every one of them is a credential to hold, a rate limit to respect, an outage window to survive and a schema that can change without telling you. Underneath them sit 9 Postgres databases, 9 vector indexes and 5 edge SQL databases - kept deliberately separate so one client's corpus can never answer from another's.

AI and research	Anthropic, Perplexity, Exa, plus edge models from four different labs
Money	Plaid, linked to Chase, Bank of America, Ally and E*TRADE - 29 accounts across 6 connections - plus Stripe for checkout and subscriptions across brands
Publishing	Ghost across eleven instances, HubSpot on one portal behind the brand sites, WordPress
CRM and messaging	GoHighLevel across 8 brand sub-accounts, Apollo, Resend, EZTexting, Twilio, Meta
Documents and media	PandaDoc, SignWell, Anvil, Dropbox, Adobe Stock, Plaud
Project and monitoring	Plane, Atera, Miro
Infrastructure	Cloudflare - carrying 9 Vectorize indexes and 5 D1 databases at the edge - GitHub, Microsoft 365 spanning 27 mailboxes (6 owned, 21 shared), Entra for identity, Microsoft Azure, Google Workspace, Supabase across 9 Postgres databases, GoDaddy, Hostinger, Netlify, Bitwarden, Ubiquiti
Utilities	TinyURL, QR.io

Any one of these is a weekend to demo and months to make dependable. 36 of them, wired so an assistant can use them safely and you can still tell what happened afterwards, takes months - or even years.

The map

Rendering the map…

Starts fitted to your screen. Zoom in for detail, or open /fleet.mmd for the raw source.

How honest is this map?

Worker names and the count were read from the live edge API on 2026-09-13, not copied from a document.
The one-line descriptions come from the estate's own published description store - the same text that feeds the internal architecture site.
The integration count is auditable. All 36 systems are named on this page - nothing is hiding inside the number. It comes from the credential vault inventory cross-checked against worker source. Systems whose status could not be re-verified were left off rather than counted.
Client tools are shown generically. Three client cockpits and three matching corpus verifiers are live. Client identity is not published here.
Nineteen workers have no written description anywhere - their knowledge-base cards are auto-generated stubs. Their lines here were derived from live configuration - routes, bindings, service links, schedules - rather than invented. That gap is a real finding, and it is left visible rather than papered over.
This page is a snapshot. The internal map reads the fleet live on every request; a public page deliberately does not call the account API.