Introducing Docen Extract

Schema-driven structured extraction with citations back to the source span.

What's new

Docen Extract gets a meaningful step up here. We spent the cycle on accuracy and consistency rather than surface-level features.

Under the hood, the model was retrained on a broader, harder set of documents, and we tightened the post-processing that turns raw predictions into clean structure.

• Improved handling of extraction.
• Improved handling of schemas.
• Improved handling of citations.

By the numbers

Getting started

The update is live on the managed API and available for self-hosted deployments. Existing integrations pick it up with no code changes — the output format is unchanged.

Want to see it on your own documents? Open the playground or reach out — we're happy to run a sample with you.