Pydantic as an AI Architecture Boundary
LLM output is not application state until it passes a typed boundary. Schemas, validation errors, evidence fields, and versioned contracts make AI workflows easier to inspect and change.
Read more
Author
AI-ToolStack
PolicyTrace Evidence and Provenance: Why JSON Is Not Enough
How PolicyTrace turns extracted insurance fields into reviewable evidence with hidden field citations, Docling geometry, provenance matching, PDF highlights, and reviewer-visible source context.
Read more
PolicyTrace
A Document AI workflow for UK motor insurance PDFs, with structured extraction, provenance, conflict resolution, and human review.
Read more