19 tasks. May 11, 2026 closed at 37.2x weighted leverage across 473.5 human-equivalent hours in 764 minutes of wall-clock time. Supervisory leverage came in at 263.1x.
That is 11.8 weeks of human-equivalent throughput in 12.7 hours. The ceiling was 240.0x; the floor was 7.6x. 16 of the 19 entries came from a single project.
Task Log
| # | Task | Human Est. | Claude | Sup. | Factor |
|---|---|---|---|---|---|
| 1 | WCAG 2.1 AA accessibility audit across 9 properties (avian-app-web + 8 accelastudy.ai marketing sites) — ~120 concrete findings with file:line refs, severity grouping, cross-cutting themes, and 6-8 dev-day… | 60.0h | 15m | 2m | 240.0x |
| 2 | Full WCAG 2.1 AA accessibility audit on avian-app-web + 8 AccelaStudy.ai sites — deterministic checker + parallel LLM judgment phase, 56 findings (7 CRITICAL, 17 HIGH, 24 MEDIUM, 8 LOW) with sequenced… | 30.0h | 17m | 2m | 105.9x |
| 3 | WCAG 2.1 AA remediation across 11 repos (avian-app-web + design-system + activities + accelastudy.ai flagship + 6 sister sites + shared template + enterprise accessibility-statement rewrite). 8 parallel fix… | 70.0h | 40m | 1m | 105.0x |
| 4 | Full WCAG 2.1 AA accessibility audit across avian-app-web and 10 AccelaStudy sites (123 findings; 13 P0 blockers identified). Consolidated report written to… | 24.0h | 18m | 3m | 80.0x |
| 5 | Debugging | 60.0h | 50m | 1m | 72.0x |
| 6 | Pre-launch security & crash audit + fix sweep across auth/purchase/onboarding/notification services: 21 issues fixed (4 CRITICAL admin gaps + IDOR, MFA bypass, webhook bypass, IDOR/spam, plus 17 HIGH), 2… | 48.0h | 55m | 8m | 52.4x |
| 7 | Testing | 14.0h | 18m | 4m | 46.7x |
| 8 | PMP demo + Adaptive Lesson Generation 2.0: plan + patentability (8 claims), atom schema+validator+composer+generator end-to-end, 6 PMP item generators producing +671 new items… | 50.0h | 90m | 5m | 33.3x |
| 9 | WCAG 2.1 AA accessibility audit of shared AccelaStudy Jinja templates (30 templates + main.js, 23 issues found) | 12.0h | 28m | 5m | 25.7x |
| 10 | WCAG 2.1 AA accessibility audit of accelastudy.ai and accelastudy.com — all templates, content pages, built HTML | 8.0h | 22m | 5m | 21.8x |
| 11 | Testing | 30.0h | 90m | 8m | 20.0x |
| 12 | Coding | 24.0h | 90m | 8m | 16.0x |
| 13 | Deployment | 1.5h | 6m | 1m | 15.0x |
| 14 | avian-admin: wire hard-delete customer flow to purchase-service GDPR endpoint so subscriptions/payments/comps cascade-delete and Stripe stops billing; receipt modal now shows purchase-side counts and Stripe… | 2.0h | 8m | 3m | 15.0x |
| 15 | Add system snapshot purge (archived + older-than modes) to avian-admin SnapshotsTab + RPC handler; fix banner save MissingGreenlet by setting eager_defaults=True on Banner model | 3.0h | 12m | 4m | 15.0x |
| 16 | CSS accessibility audit: color contrast, focus styles, motion preferences across AccelaStudy sites and avian-app-web | 6.0h | 25m | 10m | 14.4x |
| 17 | WCAG 2.1 AA accessibility audit of avian-app-web React SPA | 8.0h | 35m | 10m | 13.7x |
| 18 | Launch-day recovery: rewrote launch schedule for post-PH-flop reality (struck dead email-blast rows, added wire spend, fixed LinkedIn post date), audited homepage email-capture gap, wrote… | 16.0h | 90m | 22m | 10.7x |
| 19 | Launch-night batch: fix admin delete lockup (Valkey purge timeout), unblock avian-api CI build (ruff lint), kill TanStack 401 retry storm, rebuild + upload 4.3GB boot cache to S3, author SessionStart voice… | 7.0h | 55m | 6m | 7.6x |
Aggregate Statistics
| Metric | Value |
|---|---|
| Total tasks | 19 |
| Total human-equivalent hours | 473.5 |
| Total Claude minutes | 764 |
| Total supervisory minutes | 108 |
| Total tokens | 5,185,500 |
| Weighted average leverage factor | 37.2x |
| Weighted average supervisory leverage factor | 263.1x |
| Human-equivalent weeks | 11.8 |
Analysis
The highest factor of the day came in at 240.0x and the lowest at 7.6x, a spread of 31.4 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 60.0 of the 473.5 human-equivalent hours, or 13 percent of the day. No single task dominated the total, so the weighted average is representative.
Supervisory time was 108 minutes against 764 minutes of execution, a ratio of about 1 to 7. Supervisory leverage of 263.1x 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.