Skip to content

AI pilot licence

Every figure here is computed from the session logs. None of it is self-assessed.

AIP-2026-0126class ATP · issued 2026-03-08
Sessions126
Messages366,133
Projects69
Models flown8
Active days36
Longest streak10 d

ai-pilot-data.json, generated Sep 7, 2026

Ratings

Instrument ratings are keyword coverage over the session transcripts, so they measure what the work touched rather than how well it went. Competency scores come from the same logs and are capped at 100.

lowerhigher

Ratings0 to 100
By instrument
AI / ML79
Backend75
Security65
Systems59
Frontend49
IoT / Edge48
Data Engineering47
DevOps40
By competency
Tool Mastery95
Debugging95
Multi-Project95
Iteration76
Architecture71
Planning49

Fleet

Share of output tokens by model. Balanced piloting style: 78% collaborative, 55% plan first.

Type ratingsshare of cost
By model
opus-547.6%
fable-531.9%
opus-4-813.2%
fable-5-16.0%
opus-4-71.1%
sonnet-50.1%
opus-4-60.1%

Token economy

Tokenscumulative
Input4.0M
Output258.2M
Cache read85.6B
Cache efficiency98.4%

Token counts are abbreviated. Hover any of them for the exact figure. Pilot analytics cuts the same record by project, by hour and by day.