Agent design is still hard(lucumr.pocoo.org)
383 points by the_mitsuhiko | 219 comments
Armin Ronacher's blog post on lessons learned building AI agents, covering SDK choice, caching, reinforcement, failure isolation, shared state, and model choice.
383 points by the_mitsuhiko | 219 comments
Armin Ronacher's blog post on lessons learned building AI agents, covering SDK choice, caching, reinforcement, failure isolation, shared state, and model choice.
74 points by tosh | 54 comments
716 points by vinhnx | 454 comments
Blog post by Boris Tane describing his Claude Code workflow, centered on reviewing and approving a written plan before letting the AI write any code.