Rada

Rachet: a self-improving harness for MongoDB query tuning. Slow queries cost money and frustrate users, and fixing them takes expert time: reading explain plans, choosing indexes, and rewriting pipelines. AI agents can help, but they often overfit to the workload in front of them, or “win” by quietly changing what a query returns. RADA solves both problems. A tuning agent fixes slow MongoDB workloads, and the harness that steers it (its rules, context policy, guardrails, and tool access) improves itself from every workload it tunes. A proposer model studies past runs and suggests a new harness version. A strict gate then promotes that version only if it scores better on held-out workloads it has never seen, with every query result unchanged. If either check fails, the candidate is rejected with a reason code, and known cheats are tested and blocked. Every harness version, trace, and lesson is stored in MongoDB Atlas, so each improvement is measurable, auditable, and reversible.