Skip to main content
AI01 July 2026

Coding and content production

42 tasks. July 1, 2026 closed at 29.4x weighted leverage across 518.5 human-equivalent hours in 1,059 minutes of wall-clock time. Supervisory leverage came in at 198.2x.

That is 13.0 weeks of human-equivalent throughput in 17.6 hours. The ceiling was 80.0x; the floor was 5.0x. 40 of the 42 entries came from a single project.

Task Log

#TaskHuman Est.ClaudeSup.Factor
1Author Civics and Government knowledge taxonomy for AccelaStudy AI8.0h6m3m80.0x
2Author 94 alpha domain specs (29 languages, 10 AP gaps, 22 IB gaps, 30 K-12 grade courses, 3 pilots) via web-grounded 91-agent fan-out + generalized/hardened author_spec.py assembler; all pass structural…120.0h95m5m75.8x
3Author 115 vertical certification domain specs via 2-wave web-grounded fan-out + vendor-canonical dedup gate; survived mid-run quota interrupt with zero content loss (external backup + git); all pass…150.0h120m5m75.0x
4The Deferral: 3-round multi-agent editorial review (30 full-manuscript reads) + surgical revision (fair-play plant, thread closures, HERA seeding, opening rework, authenticity patches, 2 prose tic passes) +…70.0h90m4m46.7x
5Greek 101 knowledge taxonomy for AccelaStudy AI Languages (CEFR A1, 68 leaf goals, 8 domains)6.0h12m4m30.0x
6CAIA Level II knowledge taxonomy authorship6.0h12m3m30.0x
7Author EX280 Red Hat OpenShift Specialist knowledge taxonomy with web research8.0h18m5m26.7x
8The Deferral: full 15-reader editorial review + publication-prep structural revision (Ch31 split, boardroom scene, HERA interstitial, Finn cost arc, tic pass, Book-2 seeds, audit+docs)40.0h105m3m22.9x
9Author USMLE Step 2 CK knowledge taxonomy for AccelaStudy AI3.0h8m3m22.5x
10Czech 101 knowledge taxonomy 68 leaf goals CEFR A1 full prereq graph4.0h12m4m20.0x
11Author Hungarian 101 knowledge taxonomy (CEFR A1) — 64 leaf goals, 89 prereq edges, 6 domains4.0h12m3m20.0x
12Author CFP exam knowledge taxonomy (70 leaf goals, 8 domains)4.0h12m3m20.0x
13Author QSBA Qlik Sense Business Analyst knowledge taxonomy - 72 leaf goals across 4 official exam domains4.0h14m5m17.1x
14Author HashiCorp Vault Associate 002 exam knowledge taxonomy (63 leaf goals, 8 domains)6.0h22m5m16.4x
15Author Swedish 101 CEFR A1 knowledge taxonomy for AccelaStudy AI Languages — 8 domains, 72 leaf goals3.0h12m3m15.0x
16Grade 6 Mathematics CCSS knowledge taxonomy for AccelaStudy AI3.0h12m3m15.0x
17Author OSEP PEN-300 knowledge taxonomy for AccelaStudy AI (80 nodes, 69 leaf goals, 14 prereq edges)3.0h12m3m15.0x
18Author Turkish 101 knowledge taxonomy for AccelaStudy AI Languages (68 leaf goals, CEFR A1, ACTFL Novice)4.0h18m5m13.3x
19Author IB Theatre HL knowledge taxonomy with web research4.0h18m5m13.3x
20IB World Religions HL taxonomy authoring - 70 leaf nodes 9 domains4.0h18m3m13.3x
21Author RHCA knowledge taxonomy for AccelaStudy AI4.0h18m5m13.3x
22CIA exam knowledge taxonomy authoring (3-part IIA CIA blueprint research + 70-node flat node list)4.0h18m3m13.3x
23Thin avian-engine to code+docs: hard-gated removal of 49G package content+caches (containment analysis vs canonical+S3, 683M external backup, per-item divergence diff) + root-cause fix of relative-path…4.0h20m3m12.0x
24Author IB English Literature HL knowledge taxonomy — 73 nodes, 8 domains, 12+ prereq edges, web research3.5h18m3m11.7x
25Author CIPP/US knowledge taxonomy for AccelaStudy AI (60-80 leaf goals across 5 exam domains)4.0h22m3m10.9x
26Hebrew 101 knowledge taxonomy for AccelaStudy AI Languages3.0h18m3m10.0x
27Author Finnish 101 CEFR A1 knowledge taxonomy for AccelaStudy AI Languages — 8 domains 72 leaf goals3.0h18m3m10.0x
28Ukrainian 101 knowledge taxonomy authorship3.0h18m5m10.0x
29AP Research knowledge taxonomy authorship3.0h18m3m10.0x
30Author Databricks DE-P knowledge taxonomy with web research and official exam guide extraction3.0h18m3m10.0x
31Author GPYC GIAC Python Coder knowledge taxonomy with web-researched exam blueprint2.0h12m3m10.0x
32Author CAPA knowledge taxonomy for AccelaStudy AI3.0h18m5m10.0x
33SHRM-SCP knowledge taxonomy authoring with web research3.0h18m5m10.0x
34Author Praxis Core 5712-5722-5732 knowledge taxonomy for AccelaStudy AI2.5h18m5m8.3x
35AP Seminar knowledge taxonomy (68 leaf goals QUEST framework)3.0h22m3m8.2x
36Author CPIM knowledge taxonomy for AccelaStudy AI3.0h22m5m8.2x
37Author Alteryx Designer Core (ADC) knowledge taxonomy - 69 leaf goals across 4 exam domains2.0h18m5m6.7x
38Author CIPM knowledge taxonomy for AccelaStudy AI2.0h18m3m6.7x
39CCSK taxonomy authoring - CCSK v5 12-domain knowledge map with 70 leaf goals2.0h18m3m6.7x
40Author CFA Level III knowledge taxonomy for AccelaStudy AI2.0h18m3m6.7x
41Coding4.0h45m3m5.3x
42Author CIS-HRSD knowledge taxonomy for AccelaStudy AI1.5h18m3m5.0x

Aggregate Statistics

MetricValue
Total tasks42
Total human-equivalent hours518.5
Total Claude minutes1,059
Total supervisory minutes157
Total tokens27,965,000
Weighted average leverage factor29.4x
Weighted average supervisory leverage factor198.2x
Human-equivalent weeks13.0

Analysis

The highest factor of the day came in at 80.0x and the lowest at 5.0x, a spread of 16.0 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 8.0 of the 518.5 human-equivalent hours, or 2 percent of the day. No single task dominated the total, so the weighted average is representative.

Supervisory time was 157 minutes against 1,059 minutes of execution, a ratio of about 1 to 7. Supervisory leverage of 198.2x 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.