Ask HN: How do you build internal agents at work?

I’ve been building more and more small agents for different tasks/roles/flows.

My recent pattern: start a repo with some prompts + skills, run Codex/Claude Code, then gradually add memory and evals. That usually turns into an iterative loop of improving context, prompts, and tools based on eval results.

Curious what others are using: - Any frameworks or patterns that have worked especially well? - Anything that’s friendly for non-technical users, even without a dedicated UI?