Ask HN: Learning resources for building AI agents?

by 7e10 15 comments 13 points
Read article View on HN

15 comments

[−] tabs_or_spaces 37d ago
I find HN to be a bad resource to ask for learning resources. I previously asked for help in learning how claude works but no responses.

Maybe one pointer for others is that people are genuinely curious about learning new things, but as experts we choose not to engage these types of posts, why is that?

OP, in your case you need to move from theory into actually building your own agent and make it do things. Start by solving small problems and then make them more complex over time.

[−] anilgulecha 37d ago
The best way to learn to build an agent is to learn and use pi.dev . The homepage is a masterclass of explaining the main loop with 4 tools (read write edit bash) and how they enable any flow. Skills and Agents.md on how the agent can be guided.

If you understand the above, you're 80% of the way to building any purpose agent. System prompt, project prompt, and the tool call loop.

[−] 7e10 36d ago
this is really helpful!
[−] Storytool-io 38d ago
I think the best way for that new thing is doing some real thing/join a team building an Agent, and get some know-how.
[−] 7e10 36d ago
do you know such team? any leads?
[−] tfun 38d ago
If you want something to actually build against mastra.ai is worth a look. its typescript framework and it covers the stuff you'll run into pretty quickly. workflows, memory, RAG, observability. I didn't build anything production ready with it but it's been great for getting a feel for how these pieces fit together
[−] SerafimKorablev 38d ago
We wrote a couple of articles about it, but we were more focused on building on top of CLI-based agents like Claude Code (imagine a lead outreach agent based on Claude Code as an API).

21st.dev/community/blog

[−] sfc32 37d ago
I tried your demo at https://21st-sdk-nextjs-chat.vercel.app/?theme=light but it is timing out.

API Error: 529 {"type":"error","error":{"type":"overloaded_error","message":"Overloaded"},"request_id":"req_011CZqptSV4FbRSkAFJhfRHu"}

[−] jsilence 41d ago
Calibra might help to put some benchmark numbers on your prototypes: https://calibra.swival.dev/
[−] tianzheng-zhou 39d ago
You can ask Claude or ChatGPT for help, or study the architecture of current well-known open-source agents.
[−] OutOfHere 37d ago
I would use Microsoft Agent Framework. It is open source.
[−] adi_kurian 37d ago
Text in, text out. It's all a bunch of prompts. Use the APIs directly and avoid as many abstraction layers as possible. Everybody is figuring it out all at the same time.
[−] stochtinkerer 40d ago
Just start building my man. Would highly advise keeping it minimal, just use OpenAI Agents SDK. Most of these frameworks are overengineered af
[−] tiredgirl4 41d ago
[dead]
[−] 7e10 41d ago
yes, thanks! I have been building along the way, coded an Agent that works with google analytics 4 and some more, full stack Mern+langgraph. . however, interesting to know what others are learning.. More in the direction of building autonomous agents because using langgraph does not really seem truly autonomous or maybe i’m doing something wrong.
[−] darshil2023 40d ago
[dead]
[−] Jeffrin-dev 38d ago
[dead]
[−] maxbeech 41d ago
[dead]
[−] allinonetools_ 40d ago
[dead]
[−] Areena_28 39d ago
[flagged]
[−] Raquel_Jalves 41d ago
[dead]
[−] 7e10 41d ago
sure, thanks!
[−] yours3lf 41d ago
[flagged]
[−] tuxnotfound 39d ago
[dead]
[−] Intelligent_Fox 41d ago
[flagged]
[−] benjhiggins 41d ago
[flagged]