← All product demos

DOXA Auto-Tune Loop

DOXA audits an existing RAG pipeline from its traces, runs Bayesian optimization over chunking, retrieval, and prompts against a golden set, then promotes the winner through staged canary gates with automatic rollback. This simulation replays a representative tuning run.

Read the case study →

Simulation — real product behavior, representative data, no live API calls

This demo is live. Click the buttons inside to try it yourself.

doxa · diagnose → optimize → shadow → canary → rollback
profilingdiagnosingtuningshadowcanarypromoted

Recall@10

0.61

Faithfulness

0.68

p95 latency

2.8s

Cost / 100 queries

$4.10

▸ doxa connected to client pipeline via trace export (LangSmith format)
▸ golden set loaded: 120 question–answer pairs
▸ press Run auto-tune to start the loop

Prefer to watch?

A full run, recorded.

Screen recording of this demo completing end-to-end — same thing you can run interactively above.