Engineering

Manual field mapping was one of the most common sources of user-reported errors in Maestro workflows. Traditional semantic matching couldn't help because most eSign templates lack meaningful field labels. So we built a two-stage AI pipeline that identifies what each field represents by analyzing the document visually, then auto-maps those fields to Web Form data, cutting configuration time from 30 minutes to 20 seconds.

Every engineering team has a backlog of well-defined, repetitive tasks that consume real time but require little judgment. We built an autonomous coding agent - we call it our 'elf' - to handle that work , keeping human engineers in the review loop at every step. Here's how we built it - and how it built itself.

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.