If you're going heavy into AI coding with C# (like approaching 100% AI code), give my 5 part writeup a read. Battle tested configuration with a fast moving team that was pretty much 100% AI code with good code quality. The configuration for `csharprepl` in particular is a special kind of unlock; having the agent be able to reach into the running DI container, wrap/replace functions while app is running just unlocks a lot of capabilities for the agent. It's the difference between an ultrasound and reaching in and manipulating the organ.

Oh, thank you, this looks really helpful at this stage!

Yes, the plan is essentially 100% AI code with a small team of programmers and domain experts from other technical backgrounds. But still depends on a few things on the business end before I can really kick it off. More of an exploration until then.

I'm just starting to get a handle on how to use agents, can you give a short description of how you get your agents to use csharprepl

I have more detail written up here: https://chrlschn.dev/blog/2026/08/the-unexpected-ai-stack-cs...

But the gist of it is that I wire it up through Aspire (don't need to, but makes it nice) to set the environment variable on my main app host.

I have a small set of utility functions to access the DI container with common patterns like creating a scope for scoped services: https://github.com/zeeq-ai/zeeq-app/blob/main/src/backend/Ze... (optional, but useful)

And a skill: https://github.com/zeeq-ai/zeeq-app/blob/main/.agents/skills...

I recommend you "train" the skill like I do in my the blog post. Basically ask the agent to get an instance of an object from DI like a repository class or your DbContext and have it perform some operations. Have it wrap a function and add logging. Have it replace a function. Then once it learns how to do this, have it write the skill bespoke to your project.

That looks really awesome, thanks!