When the Law Changes, Your Agreements Should Too
Last Updated on July 27, 2026 by Editorial Team
Author(s): Rick Hightower
Originally published on Towards AI.
Building a human-in-the-loop regulatory-change agent on the Docusign MCP Server, with Claude Cowork and no code
In this article we connect the Docusign MCP Server to Claude Cowork, load real agreements, build the workflow the agent will trigger, and run the full loop conversationally, with a human approving every action.
The article walks through building a no-code “regulatory change agent” that (1) polls Docusign Agreement Manager for agreements, (2) uses Claude to extract and reason over key terms to determine which contracts are affected, (3) pauses for human approval via Cowork before any changes are made, and (4) triggers a prebuilt, governed Docusign workflow to send amendment envelopes. It covers how to attach the Docusign MCP using a custom connector (creating a developer account, generating an Integration Key, wiring OAuth redirect URIs, and verifying tool access), then loads a sample agreement corpus into Agreement Manager so the agent has real data to act on. It shows how to build and publish an amendment workflow in Workflow Builder, including an important rebuild: the first attempt stalls because manually-started, web-form steps can’t be completed by an API trigger, so the workflow is converted to an API-first start and redesigned to take signer details from trigger variables. The post then demonstrates running the full conversational loop end to end, including the human gate that prevents “green checkmark/no-op” failures, and finishes with troubleshooting lessons, reproducibility notes (sample corpus and skills/permissions files), and the key takeaway that the memo is no longer the deliverable—the triggered, approved action is.
Read the full blog for free on Medium.
Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.
Published via Towards AI
Towards AI Academy
We Build Enterprise-Grade AI. We'll Teach You to Master It Too.
15 engineers. 100,000+ students. Towards AI Academy teaches what actually survives production.
Start free — no commitment:
→ 6-Day Agentic AI Engineering Email Guide — one practical lesson per day
→ Agents Architecture Cheatsheet — 3 years of architecture decisions in 6 pages
Our courses:
→ AI Engineering Certification — 90+ lessons from project selection to deployed product. The most comprehensive practical LLM course out there.
→ Agent Engineering Course — Hands on with production agent architectures, memory, routing, and eval frameworks — built from real enterprise engagements.
→ AI for Work — Understand, evaluate, and apply AI for complex work tasks.
Note: Article content contains the views of the contributing authors and not Towards AI.
Related posts
Recent Posts
