Hacker News Reader

Comment by apwell23 | Hacker News Reader

> It's great to see at least one company creating real AI agents.

I am already doing the type of examples in that post with claude code. claude code is not just for code.

this week i've been doing market research in real estate with claude code.

I opened up the app bundle of CC on macOS and CC is incredibly simple at its core! There’s about 14 tools (read, write, grep, bash, etc). The power is in the combination of the model, the tools and the system prompt/tool description prompts. It’s kind of mind blowing how well my cobbled together home brew version actually works. It doesn’t have the fancy CLI GUI but it is more or less performant as CC when running it through the Sonnet API.

Works less well on other models. I think Anthropic really nailed the combination of tool calling and general coding ability (or other abilities in your case). I’ve been adding some extra tools to my version for specific use cases and it’s pretty shocking how well it performs!

> It’s kind of mind blowing how well my cobbled together home brew version actually works. It doesn’t have the fancy CLI GUI but it is more or less performant as CC when running it through the Sonnet API.

I've been thinking of rolling up my own too. but i don't want to use sonnet api since that is pay per use. I currently use cc with a pro plan that puts me in timeout after a quota is met and resets the quota in 4 hrs. that gives me a lot of peace of mind and is much cheaper.

Are you saying that you modified/added to the app bundle for CC?

Nope, I "borrowed" the system prompt and all the tool descriptions / tool schemas. I then re-implementing all the tools based on those descriptions and input schemas. I then used the OpenAI Agent SDK to give a model all the tools. Very conveniently the OpenAI Agent SDK supports different providers, namely the Vercel AI SDK ones, so it can be used with non-OpenAI models. The Vercel SDK has an Anthropic provider so that's how I used it to test.

This could have been somewhat trivial to implement from scratch too (not using the Agent/Vercel SDKs), but it sure made it convient! It's basically one run({model:'sonnet4', prompt: systemPrompt, tools: [tool1, tool2, tool3]}) call. Much nicer than implementing a loop and all that logic by hand.

Reply on news.ycombinator.com