Registry / 001

Built
and running.

Every entry is a real configuration of context, capabilities, activation, authority and verification—grouped by what it actually is, not by what it would be flattering to call it.

11 deployed, 1 in cutover, 1 prototype, across 10 operating environments. Every entry carries its own status: deployed entries are running in production with client identities withheld; anything not deployed says so on its own page, and implies no outcome or integration. Entries are components, not clients — several belong to the same environment. 3 of 13 publish evidence you can check without taking our word for it; the rest currently rest on our own account. Of the 3, all show a mechanism in source; none yet shows operation in production or an outcome recorded by someone other than us.

13 shown

8 of 13 entries contain no model at all. An LLM is optional — this is where that claim is checkable.

Capability / 02

Interprets and returns. Holds no authority and routes nothing.

004CapabilityProductionLLM

Document extraction

A deployed language capability that reads expense documents and returns structured fields. It interprets genuine ambiguity, holds no authority, and writes nothing — which is why it is not an agent.

Recommend authorityOperator-invoked
Inspect entry : Document extraction
005CapabilityProductionNo model

Price suggestion

A deployed pricing capability that suggests a resale price from comparable items already sold. It returns nothing rather than a guess when the evidence is too thin, and a human sets every price.

Recommend authorityOperator-invoked
Inspect entry : Price suggestion

Automation / 03

Executes a predefined path. No interpretation, no choice between actions.

003AutomationProductionNo model

Record expiry

A deployed deterministic automation that expires stale hold records in a live booking system. It runs unsupervised on a schedule, with no model and no decision in it—because the problem needs neither.

Autonomous authorityScheduled
Inspect entry : Record expiry
012AutomationProductionLLM upstream

Narration check

A deployed check that reads generated narration and refuses to let it reach voice synthesis when it carries a fault. Every rule it enforces was written after that exact fault shipped.

Autonomous authorityOperator-invokedPublished evidence
Inspect entry : Narration check
008AutomationProductionNo model

Consignment notices

A deployed automation that sends consignment deadline notices at three fixed points around the end date. It sends the matching notice or nothing at all — there is no judgment in it, and none is needed.

Autonomous authorityScheduled
Inspect entry : Consignment notices

Agent / 05

Chooses, recommends or routes a permitted action from context.

001AgentProductionNo model

Fiscal receipts

A deployed agent issuing fiscal donation receipts for a non-profit operator surface, choosing per request whether it may act and refusing when the grant is absent.

Bounded authorityOperator-invoked
Inspect entry : Fiscal receipts
002AgentPilotNo model

Order fulfilment

An agent that verifies and fulfils commerce orders from an operator upload, with an explicit dry-run boundary before any live mutation. Cut over to the shared runtime; the first live fulfilment is still pending an operator.

Bounded authorityOperator-invoked
Inspect entry : Order fulfilment
006AgentPrototypeLLM

Intake triage

A confidence-routed classifier that labels inbound message intent, resolves what it is sure of, and queues everything else for human review.

Escalating authorityBatch
Inspect entry : Intake triage
010AgentProductionNo model

Order invoicing

A deployed agent that turns retail orders into accounting invoices, deciding for each one whether to issue, skip or hand it to a human — and holding a lock so a duplicate webhook cannot invoice twice.

Escalating authorityEvent-driven
Inspect entry : Order invoicing
011AgentProductionNo model

Update verification

A deployed agent that updates live sites, then judges its own work from the outside and reverses it when the site comes back worse.

Escalating authorityOperator-invokedPublished evidence
Inspect entry : Update verification

System / 03

Combines automations, agents, humans and controls to deliver an outcome.

007SystemProductionNo model

Lesson publishing

A deployed publishing system for a financial-education library. The build recomputes every figure an author declares and refuses to produce a lesson whose arithmetic does not hold.

Assist authorityAuthor-invokedPublished evidence
Inspect entry : Lesson publishing
009SystemProductionLLM

Scene production

A deployed managed product that turns a reference image and product packshots into brand imagery. Every model step is gated by an operator, and both gates exist because their absence already caused a failure.

Recommend authorityOperator-invoked
Inspect entry : Scene production
013SystemProductionLLM upstream

Client tickets

A deployed ticketing system for an agency's client apps, where AI agents reply and requalify through the same authorization layer as people and every agent action is copied to the whole team. Approval of an agent's write is procedural: the code does not enforce it. It runs as Halo.

Recommend authorityClient-, admin- or agent-invoked
Inspect entry : Client tickets

Start with the operating problem

Tell us what is not working.

A first call is thirty minutes and costs nothing. We say honestly whether we are the right people. You would be talking to the people at We Think Beautiful in Brussels — the ones who do the work, not an account layer above them.