Five tasks. June 1, 2026 weighted to 27.4x leverage across 52.0 human-equivalent hours in 114 Claude-minutes. Supervisory leverage closed at 390.0x.
1.3 weeks of human-equivalent throughput in 1.9 hours of Claude wall-clock. The 90.0x ceiling came from ADR 0005: novel adult-learner activity set for one content domain; triaged 16 activities into 6 tiers with intellectual-property considerations, implementation plan, validation met...; the 6.7x floor sat at Two content domains to pristine+beta (cohort 30): ~6,157 questions from 0, reweighted, pairs amplified (median->15), a competence stamp, all 30 beta zero-findings, committed+pushed.
Task Log
| # | Task | Human Est. | Claude | Sup. | Factor | Sup. Factor |
|---|---|---|---|---|---|---|
| 1 | ADR 0005: novel adult-learner activity set for one content domain; triaged 16 activities into 6 tiers with intellectual-property considerations, implementation plan, validation metrics, and risk evaluation; updated ADR index | 15.0h | 10m | 2m | 90.0x | 450.0x |
| 2 | A security-scanning service Phase 1 close-out; scan endpoint + dedup-aware persistence: 5 ORM models (repos/scans/scanresults/findings/findingevents) + Pydantic schemas + orchestrator (sequential scan execution with dedup/reopen/fixed lifecycle) + 8 REST endpoints (repos/scans/findings with status PATCH + audit events) + hand-authored Alembic migration + 13 endpoint tests; full suite 186 passed / 99% coverage; committed locally | 22.0h | 26m | 1m | 50.8x | 1320.0x |
| 3 | Phase 0 of ADR-0005: extended activities catalog with 16 novel-activity entries for one content domain + 4 addons + academic category + deferred runtime_source + per-activity feature-flag plumbing + library mirror sync + 8 new tests + fixed 2 pre-existing test failures | 8.0h | 18m | 1m | 26.7x | 480.0x |
| 4 | Forensic diagnosis of crashed cross-session synthesis run + safe checkpoint resume (one certification domain) | 2.0h | 15m | 3m | 8.0x | 40.0x |
| 5 | Two content domains to pristine+beta (cohort 30): ~6,157 questions from 0, reweighted, pairs amplified (median->15), a competence stamp, all 30 beta zero-findings, committed+pushed | 5.0h | 45m | 1m | 6.7x | 300.0x |
Aggregate Statistics
| Metric | Value |
|---|---|
| Total tasks | 5 |
| Total human-equivalent hours | 52.0 |
| Total Claude minutes | 114 |
| Total supervisory minutes | 8 |
| Total tokens | 510,000 |
| Weighted average leverage factor | 27.4x |
| Weighted average supervisory leverage factor | 390.0x |
| Human-equivalent weeks | 1.3 |
Analysis
The day's leverage distribution matters more than the headline figure. The 90.0x ceiling came from ADR 0005: novel adult-learner activity set for one content domain; triaged 16 activities into 6 tiers with intellectual-property considerations, implementation...; the 6.7x floor was Two content domains to pristine+beta (cohort 30): ~6,157 questions from 0, reweighted, pairs amplified (median->15), a competence stamp, all 30 beta zero-findin.... Tasks at the top of the distribution share a shape: tightly-scoped specifications, clear success criteria, and minimal integration ambiguity. The AI doesn't need to discover anything new; it executes against an explicit target.
Tasks at the bottom run differently. They're either bounded by review-heavy work where every step gets verified, or they involve ambiguity that demands several rounds of trial and adjustment. The factor is real and informative, not a failure mode.
The supervisory leverage figure (390.0x today) tracks something orthogonal to wall-clock leverage. It's the ratio of human-equivalent output to human prompt-writing time. It stays high even on lower-leverage days because supervisory minutes scale with task count, not with the human-hour estimate; a 20-minute task and a 4-hour task can both be specified in two minutes of human prompt-writing.
Across the 5 tasks, the day produced roughly 1.3 weeks of senior-engineer-equivalent throughput in 1.9 hours of model wall-clock. That ratio is the practical answer to the question of how much output a single operator can move per day when the model handles the execution and the operator handles the direction.