17 tasks. May 17, 2026 weighted to 10.8x leverage across 309.0 human-equivalent hours in 1723 Claude-minutes. Supervisory leverage closed at 228.9x.
7.7 weeks of human-equivalent throughput in 28.7 hours of Claude wall-clock. The 96.0x ceiling came from Origin-extract Phase 3 — populate services/an origin service with synthesis code, merged backend, /jobs API + structlog observability, aoctl CLI, and relocated test surface (522 pa...; the 1.0x floor sat at Decoy zero-sweep on reclassified cloud cert packages: engine restart, fixed autopilot_service NameError (missing import os), ran sweep, 2 real terminals (AZ-120 crossed 0.5 readine....
Task Log
| # | Task | Human Est. | Claude | Sup. | Factor | Sup. Factor | ||
|---|---|---|---|---|---|---|---|---|
| 1 | Origin-extract Phase 3 — populate services/an origin service with synthesis code, merged backend, /jobs API + structlog observability, aoctl CLI, and relocated test surface (522 passing service-wide, was 7). 10 commits. | 80.0h | 50m | 5m | 96.0x | 960.0x | ||
| 2 | Audit other Claude's outstanding-work report against an inference engine engine codebase; corrected stale claims and re-estimated effort | 8.0h | 11m | 6m | 43.6x | 80.0x | ||
| 3 | Cloud deployment plan for an origin service: distilled Phases 5-7 (SQS+Fargate+Bedrock wiring, frontend refactor, deploy+cutover) + Phase 8 hygiene into a single 194-line plan doc with Mermaid flow diagram, decision matrix, open questions | 3.0h | 5m | 1m | 36.0x | 180.0x | ||
| 4 | Persistence audit follow-through: all 4 fixes shipped. (1) DeltaReplicationPublisher fail-loud in cloud profile. (2) HIGH-severity in-flight exam persistence — Alembic 007activeexams + ActiveExamRow + ActiveExamRepository + write-through on createexam + cache-miss fallback on submitexam + boot-time hydrat... | 24.0h | 55m | 1m | 26.2x | 1440.0x | ||
| 5 | Refresh patent valuations and content counts across 25 a planning repo docs (business, marketing, research, README, CHANGELOG); rebuild patent-portfolio valuation framework ($60-230M floor); scrub Android-via-PWA and late-July language from funding plans and JDs to reflect native iOS+Android both launching Ju... | 14.0h | 40m | 4m | 21.0x | 210.0x | ||
| 6 | Origin-extract Phase 4: delete src/an inference engine/origin + dying preflight subdirs + origin_router + 100+ scripts; slim OriginConfig; collapse regression guard; ratchet coverage 81→82; recover 7 over-deleted test files; finalize docs across CLAUDE.md, CHANGELOG.md, plan doc — 4 commits, ~73k LOC deletion... | 16.0h | 47m | 1m | 20.4x | 960.0x | ||
| 7 | Docstring audit Phase 3 (DOCOVERSELLS rewrite): F1 fix in adminevents.py (module + livesessionpayload docstrings) for asymmetric user fallback (username->entityid; useremail->""); audit re-run verified doc-likely 1->0; PHASESTART + DOCREWRITE + PHASE_END log entries; resolution arc CLOSED | 3.0h | 10m | 1m | 18.0x | 180.0x | ||
| 8 | Deterministic docstring-vs-code audit for engine: AST-driven scripts/auditdocstrings.py with 12 categories (structural + intent-vs-impl), per-finding likelytruth heuristic (fix doc | fix code | review). 65 findings across 292 files / 3012 symbols. Surfaced reloaddomains dedupe-vs-raise pattern + 5 durable... | 12.0h | 40m | 2m | 18.0x | 360.0x |
| 9 | Docstring audit Phase 2 (FP bookkeeping): added EXCLUDEDFINDINGS set + AuditReport.addfinding() to scripts/auditdocstrings.py with 28 exact-tuple exclusions (file, line, symbol, category) retiring the 29 FALSEPOSITIVE dispositions from Phase 1. F26+F27 collapse to one tuple. Doc-likely count drops 30->1 (... | 3.0h | 10m | 1m | 18.0x | 180.0x | ||
| 10 | CI hardening (fixed silently-dead nightly leak gate in engine nightly.yml — wrong import path; dropped continue-on-error from memray steps; mirrored nightly to an origin service with 500MB import baseline) + full persistence audit across engine+service. Found 4 issues, 1 HIGH (in-flight exams not persisted; e... | 6.0h | 20m | 1m | 18.0x | 360.0x | ||
| 11 | Origin-extract Phases 6+8: an origin client frontend retargeted at an origin service via VITEORIGINAPIURL/VITEORIGINWSURL; swapped local 300-LOC bug-reporter for @an inference engine/bug-reporter on new a defect tracker Origin board; updated CLAUDE.md/README/CHANGELOG. Phase 8: contract-changes.md entry... | 8.0h | 35m | 1m | 13.7x | 480.0x | ||
| 12 | an inference engine: fix domain reload manifold dupe (if_exists policy) + 8 unit tests + endpoint regression test; live-validated by reloading 38 AWS/GCP/Azure cert packages into running engine | 5.0h | 25m | 6m | 12.0x | 50.0x | ||
| 13 | Round content metrics to nnn,nnn+ notation, fix per-domain cost from $0.17 to ~$20 end-to-end (Mercury 2 + question bank + adversarial + tribunal + lessons + scenarios + labs), strip Apple Vision Pro from all marketing/business docs (no plans to ship), bump LaTeX template needspace values to keep section head... | 4.0h | 25m | 3m | 9.6x | 80.0x | ||
| 14 | recall-tier regeneration sweep — 274 domains across cloud + non-cloud buckets, +36462 nodes, +72924 contrastive pairs, fresh audit shows 0 in-scope CRITICAL+HIGH remaining; also tribunal pass on 8 orphan-fix packages, S3 backup of 295 domains (6.94 GB), AZ-140 synthesis resume + embedder lifecycle fix, autopi... | 80.0h | 540m | 12m | 8.9x | 400.0x | ||
| 15 | Decoy zero-sweep diagnosis: fixed current_day/elo DB sync + zombie 'running' reaper + content-density auditor, traced 365-day exam-plateau to 74% of goals lacking recall foundation | 15.0h | 210m | 8m | 4.3x | 112.5x | ||
| 16 | Docstring audit Phase 1: deterministic 9-step disposition pass for 30 doc-likely findings (3 batches of 10), with verbatim docstring/code citations, call-site enumeration, and per-finding justification. Output: append-only disposition table (1716 lines, 30 finding rows + 1 correction) and append-only resoluti... | 24.0h | 360m | 20m | 4.0x | 72.0x | ||
| 17 | Decoy zero-sweep on reclassified cloud cert packages: engine restart, fixed autopilot_service NameError (missing import os), ran sweep, 2 real terminals (AZ-120 crossed 0.5 readiness=0.509 day 44 confirming recall lift; ANS-C01 partial climb to 0.204 day 48). 13 profiles untested at user request to stop. | 4.0h | 240m | 8m | 1.0x | 30.0x |
Aggregate Statistics
| Metric | Value |
|---|---|
| Total tasks | 17 |
| Total human-equivalent hours | 309.0 |
| Total Claude minutes | 1723 |
| Total supervisory minutes | 81 |
| Total tokens | 10,907,000 |
| Weighted average leverage factor | 10.8x |
| Weighted average supervisory leverage factor | 228.9x |
| Human-equivalent weeks | 7.7 |
Analysis
The day's leverage distribution matters more than the headline figure. The 96.0x ceiling came from Origin-extract Phase 3 — populate services/an origin service with synthesis code, merged backend, /jobs API + structlog observability, aoctl CLI, and relocated...; the 1.0x floor was Decoy zero-sweep on reclassified cloud cert packages: engine restart, fixed autopilot_service NameError (missing import os), ran sweep, 2 real terminals (AZ-120.... 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 (228.9x 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 17 tasks, the day produced roughly 7.7 weeks of senior-engineer-equivalent throughput in 28.7 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.