Turn Dynamics 365 tickets into signed-off designs and tested X++ code

Nikhil Vankayalapati built eight Claude Code agents for Dynamics 365 F&O that analyse a ticket, wait for design sign-off, then write and build X++. A vendor-on-hold ticket passed all four tests on the first run.

Done withClaude Code· Nov 17, 2026

What they did

Vankayalapati, a Dynamics 365 Finance and Operations developer, wrote a team of eight agents (an architect plus finance, supply chain, security, reporting, developer, reviewer and QA specialists) and runs them in a Code session of the Claude desktop app on a D365 repo. They sit on d365fo-mcp-server, an open-source MCP server by Filip Manas that indexes the real metadata on the dev machine and lets the model search objects, validate code, build and run the best-practice check. The user only talks to the architect, which decides which specialists a ticket needs. Each agent's tool list is its permission list, so only the developer can write X++. PowerShell hooks outside the model record a sign-off tied to the exact design version and block any metadata write or build without it. Every step leaves a file in the repo: assessments, functional and technical designs, build log, review, QA result and a UAT script.

How it went

On a short test ticket asking that purchase orders for vendors on hold not save, the architect found the standard code already refused the save and only warned, so it proposed a smaller fix: a Chain of Command extension on the account check, one label and four SysTests. After the author typed go, the developer agent wrote and built them, and all four tests passed in Visual Studio on the first run. The agents are re-run against 23 sample tickets scored on eight checks. Database sync, deploy and test runs still happen by hand in Visual Studio.

Worth knowing

This is the author's launch post for his own free, MIT-licensed project, and it was only verified on UDE environments in the Claude desktop app; cloud-hosted VMs and GitHub Copilot are untested. A full ticket burns far more tokens than a chat answer. The approval hooks match commands as text, so they stop mistakes, not a user set on bypassing them.

Try it

With Claude Code· 4 parts to fill in

You are the architect for changes to [my ERP or codebase]. For this ticket: [ticket text]. First read the existing standard code and metadata through [my MCP server or code search] and check what already happens before proposing anything. Write a short design: the mechanism, every object you will add or change, what you rejected and why, security impact, and the tests. Stop and ask me for an explicit go on that design version. Only after I approve, write the code, build it and run [lint or best-practice check] and the tests. If the design has to change, stop and ask again. Finish with a review against the design and a step-by-step acceptance test script.

Square brackets are the parts to fill in. The prompt is ours; the story is theirs.

Where they said it

Related