Skip to content

Search is only available in production builds. Try building and previewing the site to test it out locally.

Intelligence

The Intelligence group turns raw telemetry into actionable signals — what’s breaking your flow, where you’re getting throttled, and how to act on it.

ItemRouteWhat it showsRead more
Throttle/insights/throttleRate-limiting events, latency spikes, and recurring drop-off detection — plus hours lost
Rightsizing/insights/rightsizingModel selection and tier recommendations based on your usage patterns
Tokens/insights/tokensToken usage breakdown — cached read/write, output, per model
Report/my/reportChapter-based personal review with trends, strengths/weaknesses, and worst promptsMy Report

These are grouped here because they’re behavioral signals, not top-line scores. They also appear from the PRISM Score page as drilldowns.

ItemRouteWhat it shows
Iteration Efficiency/insights/ieConvergence + Recovery trend
Context Reset Rate/insights/crrHow often you /compact or /clear
Flow Continuity/insights/fcMedian minutes of uninterrupted coding per session
Quality Retention/insights/qrFraction of AI output that survived review
Rework & Loop Rate/insights/rlrHow often recent work needed redoing

Once your session data lands, the Prism Engine’s background workers run sub-session aggregation, rubric scoring, and Layer 3 assembly. Most insights here update within a few minutes of a session ending — no manual refresh needed.