Docusign AI Team

Docusign processes more than a million documents a day, but 50+ standard extraction fields can’t cover everything an enterprise needs to pull from its contracts. In part three of our series on how Docusign processes contracts at scale, we cover how customers define their own extractions and run them on the same pipeline as our standard models.

Running a frontier model on every document doesn't scale at 1M+ contracts a day. In part two of our series on how Docusign contracts agreements at scale, we cover how we trained a smaller, faster model to match — and in production, beat — the accuracy of the larger model it replaced, at a fraction of the cost.

Docusign's AI engine processes over a million contracts a day, extracting more than 50 data points per document at sub-cent inference cost. This is the first post in a four-part series on how we built that pipeline, starting with the orchestration architecture that routes every document through pre-processing, model inference, and validation at enterprise scale.