Skip to main content
AI18 May 2026

Testing and infrastructure

5 tasks. May 18, 2026 closed at 30.4x weighted leverage across 190.0 human-equivalent hours in 375 minutes of wall-clock time. Supervisory leverage came in at 518.2x.

That is 4.8 weeks of human-equivalent throughput in 6.2 hours. The ceiling was 120.0x; the floor was 13.6x. 5 of the 5 entries came from a single project.

Task Log

#TaskHuman Est.ClaudeSup.Factor
1Review avian-admin and author full Stitch prompt for Westworld Delos-themed WebGL/Rive redesign covering all 24 pages, design tokens, component vocabulary, motion language, audio design, and fidelity grading…24.0h12m3m120.0x
2[ip-cluster] V2 viewer Phases 1-3: Three.js stage layer (paper-grain + page-turn shaders, mastery candle, postprocessing), Rive Living Diagrams integration (validator update in engine), layer-registry slot…45.0h35m1m77.1x
3Design and frontend16.0h28m6m34.3x
4AVIAN autopilot Fix A: coverage damping + hard ceiling on readiness. SOA-C02 baseline 36/73 KG goals at exam_passed→ 73/73 covered + passed; 36/38 cloud certs hit full per-goal coverage across AWS/GCP/Azure…100.0h278m10m21.6x
5Docstring audit Phase 7 (Protocol contract enforcement): new audit script (scripts/audit_protocol_contracts.py, 857 LoC) with AST-based one-hop expansion through same-class helpers AND field-attribute…5.0h22m2m13.6x

Aggregate Statistics

MetricValue
Total tasks5
Total human-equivalent hours190.0
Total Claude minutes375
Total supervisory minutes22
Total tokens1,416,500
Weighted average leverage factor30.4x
Weighted average supervisory leverage factor518.2x
Human-equivalent weeks4.8

Analysis

The highest factor of the day came in at 120.0x and the lowest at 13.6x, a spread of 8.8 times between the two. That is a wide range for a single day, and it usually means the day mixed mechanical work with work that needed real judgement.

The largest single entry accounted for 24.0 of the 190.0 human-equivalent hours, or 13 percent of the day. No single task dominated the total, so the weighted average is representative.

Supervisory time was 22 minutes against 375 minutes of execution, a ratio of about 1 to 17. Supervisory leverage of 518.2x is the figure I find most honest, because it measures the hours I actually spent rather than the hours a machine spent on my behalf.

Every figure here is recorded at the time the work is done rather than reconstructed afterwards. The human estimate is my own judgement and carries the uncertainty that implies; the minutes and tokens are measured. The full dataset, including this day, is available for download.