Lessons from Building Claude Code: Seeing like an Agent

x.com · 1,498 words · saved by 1 readers

To view keyboard shortcuts, press question mark View keyboard shortcuts Lessons from Building Claude Code: Seeing like an Agent Thariq @trq212 · Feb 27 Follow 218 1.4K 9.9K 3.5M One of the hardest parts of building an agent harness is constructing its action space. Claude acts through Tool Calling, but there are a number of ways tools can be constructed in the Claude API with primitives like bash, skills and recently code execution (read more about programmatic tool calling on the Claude API in @RLanceMartin's new article). Given all these options, how do you design the tools of your agent? Do you need just one tool like code execution or bash? What if you had 50 tools, one for each use case your agent might run into? To put myself in the mind of the model I like to imagine being given a difficult math problem. What tools would you want in order to solve it? It would depend on your own skills! Paper would be the minimum, but you’d be limited by manual calculations. A calculator would

One of the hardest parts of building an agent harness is constructing its action space. Claude acts through Tool Calling, but there are a number of ways tools can be constructed in the Claude API with primitives like bash, skills and recently code execution (read more about programmatic tool calling on the Claude API in @RLanceMartin's new article). Given all these options, how do you design the tools of your agent? Do you need just one tool like code execution or bash? What if you had 50 tools, one for each use case your agent might run into? To put myself in the mind of the model I like…

Lessons from Building Claude Code: Seeing like an Agent

related reading