AI engineering for companies with the data but not the AI team

Can run inside your networkDocumentsDatabasesSpreadsheetsRetrievalKnowledge GraphSearchAnswersAgents
Can run inside your networkDocumentsDatabasesSpreadsheetsRetrievalKnowledge GraphSearchAnswersAgents

What we build

  • Knowledge and retrieval systems

    Search, question answering and agents over your documents and databases, built on retrieval and knowledge graphs.

  • Private deployment

    Open models served inside your own network with vLLM or Ollama, and tuned to the hardware you have. For data that can't go to a third-party API.

  • Architecture review and evaluation

    A written review of your design, model choices and running costs. We test candidate models against your own tasks before you commit to one.

Services and how an engagement runs ›

Work

FMCG company

10 weeks

Spreadsheetssales dataDatabaserelationalKnowledge GraphLLM agentLeadershipquestionsYear on year, across regionsMargins up 3–8%Faster leadership decisionsSmaller analytics team needed
Spreadsheetssales dataDatabaserelationalKnowledge GraphLLM agentLeadershipquestionsYear on year, across regionsMargins up 3–8%Faster leadership decisionsSmaller analytics team needed

Public-sector client

14-week pilot

Their infrastructureQuestionRoutingLocal modelcommon questionsLarger modelcomplex questionsOfficerlow confidence
Their infrastructureQuestionRoutingLocal modelcommon questionsLarger modelcomplex questionsOfficerlow confidence

Knowledge Engine, our flagship product

superseded bySupplier emailMarchContract updateJune4 weekslead time · prior6 weekslead time · currentClaimSupplier lead timeSource keptPrior version kept
Supplier emailMarchContract updateJune4 weekslead time · prior6 weekslead time · currentClaimSupplier lead timeSource keptPrior version kept
See the Knowledge Engine ›

How an engagement runs

What does your team need to find, and where does it live today?

Contact us ›