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?

2 comments

[ 2.0 ms ] story [ 11.8 ms ] thread

verdverm 5mo ago ↗

I use ADK-go (also available in py, ts, java)

https://google.github.io/adk-docs/get-started/about/

alexhans 5mo ago ↗

It really depends on the type of agent and problem but your path resonates as a way to slowly build more complexity as you start understanding the uncertain space. I've written about it in my blog with the intent of helping non tech users [1] and also created a site with cookbooks and eval tool comparisons [2].

I've successfully managed to get non technical users into the terminal, even before Agent Skills were a thing. It's absolutely doable.

If any of what I share helps or you have any feedback/questions let me know. I'm quite interested to see if the framing works.

- [1] https://alexhans.github.io/posts/series/evals/building-agent...

- [2] https://ai-evals.io/