FOR .NET TEAMS | AI AGENTS GENERATE PRODUCTION CODE
Your team has the tools. I make sure the way of working grows with them, safe and maintainable, while we ship features together. I join your sprint, bring in spec-driven development and review discipline, and let your team take it over. With Claude Code, GitHub Copilot or a multi-provider setup, whatever fits your team.
No training from a distance. Building along and showing how it's done.
Your developers are experimenting with GitHub Copilot, Claude Code and Cursor. But the output stays the same, only the tooling changed. The backlog grows, velocity doesn't. AI generates more code, so PRs get bigger and review pressure rises with them. It feels like the tooling changed but the way of working didn't.
You're not looking for a course. You're looking for someone who joins the sprint and shows how it's done.
Agentic coding is building software with AI agents that work autonomously in your codebase: generating code, running tests, refactoring. You specify, review and steer; the agent does the work. The difference with autocomplete is that the agent takes on whole tasks, not single lines.
For a .NET team the work shifts from typing yourself to specifying and reviewing. The gain isn't in faster typing, but in shorter lead times: less waiting, more parallel tasks, faster iterations. Provided the way of working around it is in order. If it isn't, you get 32 review rounds on a single PR and growing verification debt (articles in Dutch).
APPROACH
In three steps from experimenting to a way of working your team carries.
Where is your team now? Which tools, which concerns, which codebase. I watch before I change anything.
I set up your AI agent (Claude Code, GitHub Copilot or multi-provider), ship features, and bring in spec-driven development and review discipline. Your team sees it live.
Workflows, prompts and conventions are in place. Your team can continue on its own. I make myself redundant, that's the goal.
Safe and maintainable. That's what I steer on. AI fills missing specs with assumptions, and without review on architecture and security, mistakes slip in that only surface in production. I guard that side and keep the judgement with a human. The tool speeds things up; you stay the owner.
I build Invullen.nl entirely with Claude Code and maintain Factuur-Assist.nl (135+ customers) with it daily. 20+ years in .NET at ABN AMRO, PGGM and Van Lanschot among others. Microsoft Certified: Identity & Access (SC-300).
More about meBuilding software with AI agents that work autonomously in your codebase: generating code, running tests, refactoring. You specify, review and steer; the agent does the work. Tools like Claude Code, GitHub Copilot and Cursor make it possible. The difference with autocomplete is that the agent takes on whole tasks, not single lines.
With the right discipline, yes. AI fills missing specs with assumptions, and without review on architecture and security, mistakes slip in. I set up review moments starting at the spec, guard security and maintainability, and keep the judgement with a human. That's exactly what I steer on.
No. I work daily with Claude Code and I'm experienced with GitHub Copilot, and I also help with multi-provider setups. The approach is about the way of working, not one tool. Whichever AI provider your team uses, the principle stays the same.
I usually join two days a week, for a number of sprints. Within the first week I ship a feature in your codebase, so the team sees live how it works. After that I phase out my role; the goal is that your team can continue on its own.
That's normal and often justified. Resistance rarely sits in the tooling. I name the unspoken concerns and bring the team along, instead of convincing with yet another demo.
A 30-minute call. I listen, ask about your stack and team, and give an honest assessment: where the gain is and whether I'm the right person.