Golden traces
Curate a pack of golden traces — the canonical examples of correct behaviour. Every promotion candidate runs against the pack.
All verticals
BetaIntelligence
DreamLab.
Bounded eval and promotion pipeline. VMI evaluation harness with golden traces, pack scoring, regression detection, and governed self-improvement gates.
What it does
Built around DreamLab.
Regression detection
Score deltas surface regressions before they ship. Per-metric gates can block a promotion until the regression is reasoned about.
Governed self-improvement
Auto-research loop. Time-bounded experiments. If the result improves the metric, commit. If it regresses, reset. The codebase ratchets forward.
Per-user feedback
Each user's thumbs up / thumbs down flows into DreamLab as labelled traces. Personal models stay personal; org models stay org-scoped.
Screens
See DreamLab in motion.
Golden trace pack with per-trace score deltas
Regression gate blocking a candidate promotion
Auto-research log with reset and commit decisions
Final screenshots ship alongside the public launch. Slots above match the canonical DreamLab surface today.
How to access
Pick a plan that includes DreamLab.
NOME Pro
Personal trace packs, basic regression gates.
NOME Team
Shared packs, team-scoped feedback, promotion approvals.
NOME Enterprise
Dedicated eval compute, BYO models, audit export.
Roadmap
What ships next.
Q2
Pack marketplace
Install community-curated golden trace packs by vertical.
Q3
Counterfactual replay
Replay a trace with a new model to score head-to-head deltas.
Q3
Live A/B routing
Promote candidates to a percentage of live traffic with safety gates.
Try DreamLab in NOME.
One platform. Every vertical. Switch between DreamLab and the rest of NOME without losing context.