←back to thread

Building your own CLI coding agent with Pydantic-AI

(martinfowler.com)
196 points vinhnx | 3 comments | 28 Aug 25 18:34 UTC | HN request time: 0s | source
Show context
iLoveOncall ◴[28 Aug 25 20:13 UTC] No.45056540[source]▶
I really wish Pydantic invested in... Pydantic, instead of some AI API wrapper garbage.

I've been using it a lot lately and anything beyond basic usage is an absolute chore.

replies(3): >>45056749 #>>45057785 #>>45057990 #
DouweM ◴[28 Aug 25 22:59 UTC] No.45057990[source]▶
I'm curious what issues you've run into, do you happen to have GitHub links so I can have a look? (I'm a maintainer.)

Pydantic still sees multiple commits per week, which is less than it was at one point, but I'd say that's a sign of its maturity and stability more than a lack of attention.

replies(1): >>45058853 #
1. __MatrixMan__ ◴[29 Aug 25 01:07 UTC] No.45058853[source]▶
My experience is that pretty frequently the LLM just refuses to actually supply json conforming to the model and summarizes the input instead. Even with several retries configured I still couldn't rely on it. I only spent an afternoon with it though so it's possible I'm just doing it wrong (either in how I'm prompting or in how I'm configuring pydantic-ai).
replies(1): >>45059019 #
2. DouweM ◴[29 Aug 25 01:33 UTC] No.45059019[source]▶
How recently was that? I made a few improvements earlier this month: https://news.ycombinator.com/item?id=45058214

If the issue is still showing on the latest version, seeing the Pydantic model/schema would be very helpful.

replies(1): >>45059643 #
3. __MatrixMan__ ◴[29 Aug 25 02:58 UTC] No.45059643[source]▶
It was about a month ago. I'll take another swing at it and make an issue if I can't overcome it.

Thanks for being a proactive kind of maintainer. The world is better because of people like you.