Engineering

AI code review tools are leaving more comments than ever, but processing them mindlessly (rubber duck debugging) can be just as risky as ignoring them. Docusign engineers share how they built a custom AI agent to turn PR feedback into a real conversation, not just a faster way to click "resolve."

LLMs are powerful but inconsistent, and in contract review, small errors can be costly. Here's how Docusign's AI team built a fast, no-code evaluation system to continuously test, measure, and improve the accuracy of our contract review assistant.