I think there's a lot that doesn't get built initially especially around error management and more feature completeness around how the response will be shaped. I think it's an interesting demonstration in how to leverage an existing system of services for AI but definitely more to do. Thanks for asking.
Edit: One other thing I kept out was code generation — the agent can call services but doesn't create them. I've just built it: `micro run --prompt "a task management system"` generates real services, builds them, starts them, and the agent can use them immediately. The agent can build new services on the fly.
Dang I made the same thing the same day https://news.ycombinator.com/item?id=48374308
Very cool.
There's a lot of complexity around AI agents right now, so I appreciate examples that keep things simple and easy to understand.
Did building it in such a small codebase require leaving out any features you originally wanted?
I think there's a lot that doesn't get built initially especially around error management and more feature completeness around how the response will be shaped. I think it's an interesting demonstration in how to leverage an existing system of services for AI but definitely more to do. Thanks for asking.
Edit: One other thing I kept out was code generation — the agent can call services but doesn't create them. I've just built it: `micro run --prompt "a task management system"` generates real services, builds them, starts them, and the agent can use them immediately. The agent can build new services on the fly.
Blog post here: https://go-micro.dev/blog/13