Studio experimentDocument intelligence2025
Ledger
A document pipeline that extracts structured records from inconsistent supplier invoices, validates them in code, and routes only its own uncertainty to a person.
Selected work
Three systems, documented honestly.
Each of these was built to answer a question we kept running into. They are written up the way we would want to read them: architecture, decisions, how they were tested, and what they do not do.
- Pieces
- 3
- Provenance
- Studio experiments and concept demonstrations
A note on provenanceNothing on this page is client work. These are projects the studio built itself, so they carry no customer names, no testimonials and no production metrics. Each is labelled Studio experiment or Concept demonstration, and each ends with the things it does not prove.
Concept demonstrationConversational analytics2025
Prism
A natural-language interface to a data warehouse that generates read-only queries inside permission boundaries and shows the definition behind every number it reports.
Studio experimentAgentic workflows2025
Relay
An operations workflow that triages inbound requests, acts on the routine ones within written policy, and escalates everything else with its context already assembled.
07Next step
Have something difficult in mind?
We like ambitious problems — the ones with awkward constraints, messy data and a real cost attached to getting them wrong. Tell us what you are building and what makes it hard.
- Good fit
- A real workflow with real constraints, an internal owner who can make decisions, and a problem where being wrong actually matters.
- Less good fit
- A chatbot with no defined job, a fixed-scope rebuild of something that already works, or a project that needs to look finished before it is understood.