Claude
2 articles tagged Claude.
Tool use explained: how an LLM calls your code
A language model can't run code or hit an API. It can only ask you to. This post explains how tool use works, what the model actually sees, and where things quietly go wrong.
How the agent loop works, step by step
Every agent runs the same loop: send the conversation, get back text or a tool request, run the tool, append the result, repeat. This post walks through one full run and the bugs that trip people up.