News for hackers. Stuff that matters.
Re:Building an AI agent inside a 7-year-old Rails monolith by timrogers on Friday December 26, 2025 @07:54AM (#46391570)
That would be the normal pattern. But you could certainly stop after the LLM picks the tool and provides the arguments, and not present the result back to the model.

There are no comments on this comment yet.