AI pilot licence

Every flight, on the record: the work I ship with Claude as co-pilot, counted from the session logs. None of it is self-assessed.

Totals cover the period since 8 March 2026, through 7 November 2026, read from the durable activity record. That record has been kept since 7 July 2026. From before then it holds only the sessions whose logs were still on disk, so the earlier months are incomplete. A message is one transcript record: a prompt, a tool result or one block of a model reply.

AI pilot licencechecking

Federation of AI Aviation

AIP-2026-7094

Bradley Isenbek

Airline transport · Multi-engine (10 models) · Instrument rated (8 ratings)

ClassATP

Issued: 8 March 2026
Expires: NEVER
Last entry: 7 November 2026

Sessions: 7,094; flights logged
Messages: 1,575,374; transcript records
Tool calls: 495,301; made by the model
Projects: 141; directories flown from
Models flown: 10; type ratings below
Active days: 223; of 245 in the period

ai-pilot-data.json license and streaks, 8 Mar to 7 Nov 2026, generated 6 November 2026

Class ATP is a volume band: more than 300,000 transcript records. The serial is the session count, the issue date is the first day in the record, and the two lines at the foot repeat the card in machine-readable form. In flight means a Claude Code session on this host wrote to its log in the last five minutes; sessions on my second machine are not seen from here.

Logbook

The last 24 hours first, counted a minute at a time. Then the whole record: every day since 8 March 2026, with each week's total over its column, and the hours of the day the work lands in.

Claude Code, last 24 hourslast heard 7 Nov 2026 02:03 UTC

732 min active in the last 24 h

2 so far this hour, 29 in the hour before. Claude Code sessions on this host only.

Active minutes per clock hour (UTC)

tallest 53 min

Active minutes per clock hour (UTC)
Bucket	min
6 Nov 02:00 UTC, part hour	32
6 Nov 03:00 UTC	24
6 Nov 04:00 UTC	32
6 Nov 05:00 UTC	29
6 Nov 06:00 UTC	34
6 Nov 07:00 UTC	25
6 Nov 08:00 UTC	28
6 Nov 09:00 UTC	16
6 Nov 10:00 UTC	15
6 Nov 11:00 UTC	16
6 Nov 12:00 UTC	16
6 Nov 13:00 UTC	17
6 Nov 14:00 UTC	53
6 Nov 15:00 UTC	31
6 Nov 16:00 UTC	48
6 Nov 17:00 UTC	37
6 Nov 18:00 UTC	36
6 Nov 19:00 UTC	15
6 Nov 20:00 UTC	48
6 Nov 21:00 UTC	46
6 Nov 22:00 UTC	43
6 Nov 23:00 UTC	26
7 Nov 00:00 UTC	34
7 Nov 01:00 UTC	29
7 Nov 02:00 UTC, hour in progress	2

Counted once a minute by a cron on this host. Last count 7 Nov 2026 02:03 UTC

public/data/activity-pulse.json: rewritten every minute, this host only

Every day on the record223 active days of 245

Current streak, the longest: 164 days; 28 May to 7 Nov, every day
Busiest day: 26,067; records on 3 November 2026
Busiest week: 105,773; records, week of 12 October 2026

Transcript records per day and per calendar week, 8 March 2026 to 7 November 2026

tallest week 105,773 records

One cell is one UTC day, 2026-03-08 to 2026-11-0701 to 657658 to 4,4924,493 to 8,4278,428 to 11,72711,728 to 26,067recordsbusiest day

Transcript records per day and per calendar week, 8 March 2026 to 7 November 2026, by month
Month	records	Active days	Days in window
2026-03	1,846	15	24
2026-04	14,057	24	30
2026-05	25,226	24	31
2026-06	161,610	30	30
2026-07	245,101	31	31
2026-08	350,793	31	31
2026-09	288,261	30	30
2026-10	383,400	31	31
2026-11	105,080	7	7

A streak is consecutive UTC days with at least one record. The bar over each column is that calendar week, Monday to Sunday. The first and last are part weeks. The pale months at the start are not a slow start: the record has been kept since 7 July 2026, and before that it holds only the sessions whose logs were still on disk.

Hours of the dayAmerica/Detroit

Transcript records by hour of day (America/Detroit)

tallest 126,612 records

Transcript records by hour of day (America/Detroit)
Bucket	records
00:00 America/Detroit	47,860
01:00 America/Detroit	36,640
02:00 America/Detroit	17,316
03:00 America/Detroit	9,270
04:00 America/Detroit	5,631
05:00 America/Detroit	5,159
06:00 America/Detroit	7,044
07:00 America/Detroit	10,893
08:00 America/Detroit	43,155
09:00 America/Detroit	65,339
10:00 America/Detroit	86,457
11:00 America/Detroit	95,825
12:00 America/Detroit	100,076
13:00 America/Detroit	109,007
14:00 America/Detroit	121,664
15:00 America/Detroit	126,612
16:00 America/Detroit	111,511
17:00 America/Detroit	107,478
18:00 America/Detroit	83,179
19:00 America/Detroit	68,561
20:00 America/Detroit	78,202
21:00 America/Detroit	82,130
22:00 America/Detroit	86,113
23:00 America/Detroit	70,252

Sessions started by hour of day (America/Detroit)

tallest 328 sessions

Sessions started by hour of day (America/Detroit)
Bucket	sessions
00:00 America/Detroit	276
01:00 America/Detroit	292
02:00 America/Detroit	276
03:00 America/Detroit	268
04:00 America/Detroit	272
05:00 America/Detroit	273
06:00 America/Detroit	270
07:00 America/Detroit	267
08:00 America/Detroit	278
09:00 America/Detroit	303
10:00 America/Detroit	304
11:00 America/Detroit	316
12:00 America/Detroit	328
13:00 America/Detroit	305
14:00 America/Detroit	320
15:00 America/Detroit	328
16:00 America/Detroit	325
17:00 America/Detroit	313
18:00 America/Detroit	311
19:00 America/Detroit	297
20:00 America/Detroit	296
21:00 America/Detroit	303
22:00 America/Detroit	281
23:00 America/Detroit	292

Hours of the day in America/Detroit, summed over the whole period. The bar marked now is the hour it is there as you read this.

ai-pilot-data.json activityHeatmap, hourlyDistribution and streaks, 8 Mar to 7 Nov 2026, generated 6 November 2026

Models flown

10 models, each drawn from the first day to the last day it appears in the record. The figure on the right is its share of all output tokens, and the type rating is a band of that share and nothing more: Expert above 50%, Proficient above 20%, Familiar above 5%, Exposure below that.

Type ratingsshare of output tokens

When each model was flown, 8 March 2026 to 7 November 2026

Opus 5Proficient · 26 Jul to 6 Nov · 143,944 responses27.9%

Opus 4.8Proficient · 28 May to 16 Oct · 95,764 responses25.2%

Fable 5.1Familiar · 1 Sep to 6 Nov · 72,768 responses17.2%

Opus 5.5Familiar · 23 Sep to 7 Nov · 100,838 responses15.6%

Fable 5Familiar · 10 Jun to 23 Sep · 58,885 responses12.0%

Opus 4.7Exposure · 17 Apr to 22 Jul · 10,388 responses1.8%

Opus 4.6Exposure · 8 Mar to 27 Apr · 2,239 responses0.2%

Sonnet 5Exposure · 1 Jul to 26 Aug · 172 responses<0.1%

Sonnet 4.6Exposure · 2 Apr · 215 responses<0.1%

Haiku 4.5Exposure · 14 Jul · 1 response<0.1%

Mission log

A mission is a project, and a project is the directory a session started in, so these are directory names as they sit on disk. Each bar runs from the first active day to the last. The figure on the right is messages. Subagent logs are not counted.

Missionsbusiest 20 of 141 projects

First to last active day, and messages, 8 March 2026 to 7 November 2026

cb*, 12 directories118 sessions · 28 May to 7 Nov551,536

infra12 sessions · 6 Jun to 7 Nov129,508

terrapulse24 sessions · 29 May to 5 Nov97,246

context-agent6,615 sessions · 11 Oct to 7 Nov86,399

65025 sessions · 12 Aug to 7 Nov73,038

public1 session · 22 Aug to 5 Nov50,272

bradleyio7 sessions · 8 Mar to 3 Nov47,668

tinykit2 sessions · 14 Oct to 7 Nov25,263

The busiest 20 of 141 projects by messages. The row marked cb* is 12 directories whose names begin with cb, summed. Most are repositories in the Nominate-AI organisation, which are private. /work gives that organisation's totals without naming its repositories, and so does this log. One more is not listed at all; its sessions and messages are still in every total on this page.

ai-pilot-data.json typeRatings and missionLog, 8 Mar to 7 Nov 2026, generated 6 November 2026

Top tools

What the model reached for. 495,301 tool calls in the period, across 147 distinct tools. Most of flying is the shell.

Toolsshare of all calls

The next 8, share of all tool calls

ToolSearch1.8%

mcp__tinyagent__report1.7%

mcp__tinyagent__stamp1.6%

mcp__tinyagent__due1.3%

SendMessage1.3%

TaskUpdate0.6%

Agent0.4%

Monitor0.4%

Shares, not counts, on purpose. This list is read from the raw tool-call table, which holds some rows twice (it runs about 1.3% over the corrected total above). The duplicates are spread evenly enough that the shares hold, but the counts would not.

pilot-analytics.json by_tool, 8 Mar to 7 Nov 2026, generated 7 November 2026, the raw tool-call table of the same activity record

Ratings

Read these as rough. They measure what the work touched, not how well it went. The instrument ratings describe about the last month, not the whole record.

How these are scored

Instrument ratings come from the words in each project's CLAUDE.md, the plan files and the technologies named in the session logs still on disk, which reach back about 30 days. Each domain's score is half keyword coverage and half its mentions against the busiest domain's, and keywords are matched as plain substrings.

Competency scores are fixed formulas over counts from the record, the plan files on disk and the prompt history, and the count each one was computed from is printed under its name. Debugging assumes every shell, search and read call is debugging, which overstates it. The formulas stop at 95, and 3 scores sit at that cap. Piloting style is two ratios: directive is twice the share of tool calls that were Edit or Write, and plan first rises with plan files per session.

Ratings0 to 100

Instrument ratings, by domain

AI / ML3,714 mentions · 63% of its keywords81

Backend2,010 mentions · 89% of its keywords71

Security835 mentions · 100% of its keywords61

Systems479 mentions · 100% of its keywords56

IoT / Edge908 mentions · 79% of its keywords51

DevOps612 mentions · 78% of its keywords47

Frontend608 mentions · 77% of its keywords46

Data Engineering722 mentions · 68% of its keywords43

Competency profile

Tool Mastery147 tools, 495,301 calls95

Debugging385,221 Bash, Grep and Read calls95

Multi-Project40,013 project switches in the prompt history95

Architecture141 projects70

Iteration222 records/session avg61

Planning1 plan files on disk44

Piloting style: Balanced

Collaborativeagainst 22% directive78%

Plan firstagainst 50% iterate50%

What came up

Technologies by how often they appear in a sample of the session logs still on disk (100 files), which reach back about 30 days, and in each project's CLAUDE.md. This counts mentions, not proficiency, and it describes recent work, not the whole record.

Skills cloudtop 12 of 25

Mentions in session transcripts

JSON2,680

Nginx1,716

Python1,470

Bash1,362

SSH979

HTML978

CSS845

SQLite613

Anthropic580

systemd556

DuckDB512

YAML411

Go, Git, Rust, SPI, AWS are left out. The count matches a name anywhere inside a word, and those names turn up inside ordinary English (going, digit, trust, despite, draws), so their totals are not mentions of the technology.

ai-pilot-data.json competencyRadar and pilotingStyle, 8 Mar to 7 Nov 2026; instrumentRatings and skillsCloud, a sample of the logs still on disk (about the last 30 days), generated 6 November 2026

Token economy

What the flying burned. Nearly all of it is cache reads: the same context, read again on every turn.

Tokenssince 8 March 2026

Token totals, 8 March 2026 to 7 November 2026
Input	14.7M14,673,160
Output	427.7M427,690,539
Cache read	155.6B155,588,925,554
Cache created	2.5B2,510,766,685
Cache efficiency	98.4%of the input side
Model responses	485,214
Cost at API list price	not computed

Input plus output tokens per day, last 30 active days

tallest 5,949,320 tokens

Input plus output tokens per day, last 30 active days
Bucket	tokens
9 October 2026	1,943,564
10 October 2026	1,135,469
11 October 2026	3,063,082
12 October 2026	5,600,568
13 October 2026	2,037,163
14 October 2026	2,335,824
15 October 2026	4,335,325
16 October 2026	4,181,318
17 October 2026	1,491,845
18 October 2026	2,338,320
19 October 2026	2,400,408
20 October 2026	3,252,732
21 October 2026	2,816,251
22 October 2026	3,228,140
23 October 2026	3,916,388
24 October 2026	2,181,558
25 October 2026	1,270,161
26 October 2026	3,203,857
27 October 2026	3,357,286
28 October 2026	4,002,538
29 October 2026	4,031,446
30 October 2026	4,172,843
31 October 2026	1,093,960
1 November 2026	1,488,330
2 November 2026	3,997,073
3 November 2026	5,949,320
4 November 2026	3,670,138
5 November 2026	4,646,217
6 November 2026	3,740,880
7 November 2026	122,491

Cache tokens are not in these bars.

ai-pilot-data.json tokenEconomy, 8 Mar to 7 Nov 2026, generated 6 November 2026

Each total is shown abbreviated and, under it, exactly. Cache efficiency is cache read as a share of everything on the input side: input, cache read and cache created together. Cost is not computed: the durable record does not say whether cache writes used the 5 minute or the 1 hour TTL, which are priced differently.

How tokens are counted. Counted once per model response, not once per log line. The record does not store response ids, so a response is reconstructed from the usage counts its log lines repeat. On 2026-10-02 that rule was compared with response ids in the raw logs still on disk, about 40 percent of the record, and gave identical counts and token sums. The other 60 percent, whose logs were already pruned, is counted by the same rule and was not verified. Tokens used by subagents are not in the record.

Keep reading

This page is the receipts. Two longer reads sit beside it: The shift, the argument, and Cost analysis, the bottom-up cost model.