alt Hacker News20% tools, 40% prompt, 40% claude.md (agents.md) = 98% success most of the time. A few errors to correct is not the end of the world.
20% tools, 40% prompt, 40% claude.md (agents.md) = 98% success most of the time. A few errors to correct is not the end of the world.
Right. But "prompt" also covers a lot of ground, e.g. planning, tracking tasks, etc. The codex-style frameworks do a good amount of that for you, but it can still make a big difference to structure what you're asking the model to do and let it execute step by step.
A lot of the failures people talk about seem to involve expecting the models to one-shot fairly complex requirements.