Blog
Practical notes on measuring AI work.
Guides for imports, metrics, coding-agent telemetry, and privacy-safe analytics.
Showing 4 of 4 matching articles in Metrics · page 1 of 1 · Clear filters
Results
Metrics
How to Compare AI Usage Without Misleading Deltas
A defensible AI-usage comparison starts with two explicit slices, checks metric coverage and provenance, and keeps refused deltas visible instead of silently dropping them.
7 min read · Last reviewed 2026-08-20
Metrics
The Capability Matrix: What Each AI Export Can Actually Tell You
A source-by-source reading of the AI Stats capability matrix — Verified versus Beta, Not in export versus Not parsed yet, and why a blank Claude or Gemini tile is evidence rather than a bug.
6 min read · Last reviewed 2026-08-09
Metrics
Twelve Totals and Five Quality Labels: What the Dashboard Measures
Ranges, timezone boundaries, previous-period comparison, unavailable versus zero, and the rules that make a cost estimate refuse.
4 min read · Last reviewed 2026-07-31
Metrics
AI Active Time vs. Session Time: What Your Statistics Actually Mean
Why an AI session lasting three hours does not necessarily mean the model worked for three hours.
4 min read · Last reviewed 2026-07-31