Engineering

Every mature codebase accumulates dead code: expired feature flags, unreachable branches, logic that shipped years ago and never got cleaned up. So we built Vulture to automate cleanup. It's already removed ~150,000 lines of dead code from our legacy eSignature codebase in one year. Here's how we built it.

Contract tables — the SLA terms, rate cards, and pricing schedules buried in enterprise agreements — are among the hardest data to extract accurately at scale. Docusign has integrated NVIDIA's Nemotron Parse, a vision-language model purpose-built for document understanding, into its document processing pipeline to solve this. Table extraction powered by Nemotron Parse is now accepting beta customers with full general availability ahead.

Manual field mapping was one of the most common sources of user-reported errors in Workflow Builder 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.