Tag
The author shares their experience switching from semantic embeddings to BM25 for tool selection in agents, finding that BM25 achieves 81% top-1 accuracy vs. 64% for embeddings on a corpus of 200 query-tool pairs, because tool descriptions are short and keyword-driven rather than semantically rich like documents.
A year-long reflection on the hard parts of shipping AI agents for real service businesses, highlighting that infrastructure and edge cases matter more than the AI layer.
A developer recounts how many challenges in building AI agents actually stem from workflow and state management issues, not model intelligence, emphasizing the need for robust state handling and observability.