← redevops.io example
Observability

See the planner decide

The database gives you EXPLAIN ANALYZE; Context Runtime gives you this. For any request, watch the planner rank retrieval strategies by learned quality (not just cost), see the calibrated relevance of every candidate passage, and know exactly what it served — or why it declined to answer.

Presets are real EXPLAIN output from the runtime’s reproducible benchmark. “Run live” queries the demo control plane.

Decision — why this retrieval strategy

Every strategy the bandit can pick, ranked by learned reward. The quality and cost bars are tracked separately, so a genuinely better method wins on quality — it isn’t hidden behind a cheap-but-worse one.

learned qualitycost served

Retrieval — what each method returned

The same query through every method, with calibrated P(relevant) per hit. A red bar flags a passage with a high raw score but low real relevance — the trap a raw-score ranking falls for, made visible.

Served & reward

This is the open-source planner — the same runtime powering the chat demo and the benchmarks. Reproduce EXPLAIN locally: python examples/explain.py