Stop Over-Engineering Your AI Agent. Then Teach It What It Doesn't Know

We built an AI agent that searches across a user's emails, Slack, Jira, and other channels to answer questions like "find the Acme project update" or "list all release versions." The search was broken in ways we didn't expect — and the fixes were counterintuitive. Every instinct said add more intelligence : smarter classification, better query rewriting, self-grading loops, bigger models. Every one of those instincts was wrong. The real path had two parts: Get out of the AI's way. Most of our "i