Skip to content

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

Measurement

The Measurement group is where the raw per-prompt and per-sub-session signals live. These are the inputs the PRISM Score composites are built from — one page per metric, so you can drill into the underlying behavior rather than reading a single aggregated number.

ItemRouteWhat it showsRead more
Prompt Efficiency/prism/prompt-efficiencyPES — four-dimension prompt rubric (Context Leverage, Information Density, Turn Economy, Ambiguity Cost) with trend and worst promptsPES
Session Efficiency/prism/session-efficiencySSE — outcome anchor per sub-session, broken down by tokens / turns / human time / latency axesSSE
Iteration Efficiency/insights/ieTurns per active CLI hour, convergence patternIE
Context Reset Rate/insights/crr/compact / /clear cadence vs. the healthy-middle bandCRR
Response Latency/insights/rlrLatency distribution, regressions, and the ratio against baseline
Flow Continuity/insights/fcMedian minutes of uninterrupted focused stretchesFC
Quality Retention/insights/qrShare of AI output that survived review — feeds the Speed penalty
Token Usage/insights/tokensTokens broken out by model and by cache-read / cache-write / uncached / output

Five of these are weighted inputs into the Skill composite. The others are diagnostic: they explain why a Skill input moved.

Skill inputWeightPage
SSE45%Session Efficiency
PES20%Prompt Efficiency
IE15%Iteration Efficiency
CRR10%Context Reset Rate
FC10%Flow Continuity

Not in Skill but surfaced here:

  • Quality Retention feeds the Speed score as a penalty (low QR discounts Speed).
  • Response Latency is a raw operational metric — useful for spotting regressions but not a coaching signal.
  • Token Usage is a cost-tracking breakdown, not a quality signal.

All pages update within a few minutes of a sub-session closing. Sub-session boundaries are detected by the engine from explicit signals (/clear, /compact, session-id change), implicit signals (idle gap, intent shift), and completion signals. See Architecture for the full pipeline.