Agent engineering studio
AI agents for commerce, payments and healthcare.
We build agents that transact, work in the standards that let them interoperate, and publish the suites that prove an implementation is correct.
- 65 merged fixes upstream
- 294 validated conformance checks
- 3 standards efforts
Three practices
One discipline, three industries. Read the contract, build to it test first, prove it with a suite anyone can run.
Commerce agents
Shopping and merchant agents over a real store. Carts that survive a restart, staged changes applied once, checkout that revalidates before it takes money.
Commerce agentsPayments and protocol
Agentic checkout fails on protocol, not on prose. Signatures, idempotency, error envelopes, and schema constraints that bind.
Payments and protocolHealthcare agents
Healthcare agents stand or fall on standards and interoperability. Consent scope, audit trail, and a refusal when the safe answer is no.
Healthcare agentsProduct
Steadyline
A phone number for a small business that answers every call.
It learns the business from its own website and documents, then handles inquiry, booking, returns and refunds, and hands to a person when it should.
In development. Proof of concept complete, early access opening to anchor customers.
- One number per business. No shared queue, no shared prompt.
- Knowledge that already exists. The website and documents of the business.
- Inquiry, booking, returns, refunds. The four calls that cost the most time.
- A handover that works. The agent knows what it does not know.
The standards record
We implement specifications until they break, report what broke, and send the fix. Public and countable.