✳flâneur — a map of the web's best reading

Thariq on X: "Lessons from Building Claude Code: Seeing like an Agent " / X

x.com · 43 words · saved by 1 readers

To view keyboard shortcuts, press question mark View keyboard shortcuts Home Explore Notifications Follow Chat Grok Bookmarks Creator Studio Premium 50% off Profile More Post Emma Guo @emmaguonotion Article See new posts Conversation Thariq @trq212 Lessons from Building Claude Code: Seeing like an Agent 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 o

Thariq @trq212 Lessons from Building Claude Code: Seeing like an Agent 7:20 PM · Feb 27, 2026 4M Views 249 0 2 4 9 1.4K 0 1 . 4 K 11K 0 1 1 K 28K 0 2 8 K Read 249 replies

Explore this link on the map →

Thariq on X: "Lessons from Building Claude Code: Seeing like an Agent " / X

related reading