←back to thread

Tools: Code Is All You Need

(lucumr.pocoo.org)
313 points Bogdanp | 2 comments | | HN request time: 0s | source
Show context
tristanz ◴[] No.44456336[source]
You can combine MCPs within composable LLM generated code if you put in a little work. At Continual (https://continual.ai), we have many workflows that require bulk actions, e.g. iterating over all issues, files, customers, etc. We inject MCP tools into a sandboxed code interpreter and have the agent generate both direct MCP tool calls and composable scripts that leverage MCP tools depending on the task complexity. After a bunch of work it actually works quite well. We are also experimenting with continual learning via a Voyager like approach where the LLM can save tool scripts for future use, allowing lifelong learning for repeated workflows.
replies(1): >>44456933 #
1. JyB ◴[] No.44456933[source]
That autocompounding aspect of constantly refining initial prompts with more and more knowledge is so interesting. Gut feeling says it’s something that will be “standardized” in some way, exactly like what MCP did.
replies(1): >>44457101 #
2. tristanz ◴[] No.44457101[source]
Yes, I think you could get quite far with a few tools like memory/todo list + code interpreter + script save/load. You could probably get a lot farther though if you RLVRed this similar to how o3 uses web search so effectively during it's thinking process.