Your AI week in review

Sep 8, 2026 to Sep 14, 2026 · from Claude and Codex · everything on this page was worked out on your own computer

42.4 milliontokens processed

That is about 212 books of text read and written by AI. A token is a small piece of a word — the unit AI tools count work in. More tokens means more work, and usually more cost.

Dollar amounts are off by default because prices change and differ by plan. Add a price list you trust (see the README) and this page will show an estimate.
Busiest dayWednesday, Sep 926.1 million tokens
Heaviest promptyes please, go ahead with all of itVery heavy · 10× your typical prompt
Top conversationPlan the launch checklist for the new mobile app release28.1 million tokens · 66% of the total
Most-used modelclaude-sonnet-583% of the work
11things you asked AI to do
335individual AI steps taken
23helpers and checks started on your behalf
90%of reading reused from memory

Where did the effort go?

About 90% of what the AI read was material it had already seen — usually cheaper and faster than reading it fresh.

Who did the work?

12% of the work happened behind the scenes — helpers, hand-offs and safety checks you never typed a message for.

Which conversations used the most?

Each conversation includes the helpers, hand-offs and safety checks it started. The name is how the conversation began.

Show the top 25 with their IDs
ConversationIDPromptsHelpersTokens
Plan the launch checklist for the new mobile app releasedemo-c131228,149,977
Compare three vendors for the analytics migrationdemo-c3236,826,874
Fix the flaky login test and explain the root causedemo-x1163,744,206
Draft the quarterly board update from these notesdemo-c2201,890,908
Rename the internal config keys across the repodemo-x212853,971
Summarise last week's customer support ticketsdemo-c410797,347
Translate the onboarding email into Bahasa Indonesiademo-c51097,179

To look at just one, pass its ID to --session on any command.

Which tasks were the heaviest?

Your typical task was about 1.8 million tokens. Tap a row to see what happened inside it.

1yes please, go ahead with all of itSep 9, 2026 · Claude · Team effortVery heavy18.1 million tokens
≈ 90 books · 10.2× typical

100 AI steps · 7 helpers involved · held up to ~509 pages in mind at once

  • Your conversations: 15.8 million
  • Work handed to Codex: 1.5 million across 2 sessions
  • Helpers the AI started: 360 thousand across 1 session
  • Automatic safety checks: 363 thousand across 4 sessions

Models used: claude-sonnet-5, codex-auto-review, gpt-5.6-sol

2add the rollout risks and ownersSep 9, 2026 · Claude · Multi-stepHeavy8.0 million tokens
≈ 40 books · 4.5× typical

24 AI steps · 1 helper involved · held up to ~571 pages in mind at once

  • Your conversations: 8.0 million
  • Automatic safety checks: 55.0 thousand across 1 session

Models used: claude-sonnet-5, codex-auto-review

3Compare three vendors for the analytics migrationSep 11, 2026 · Claude · Team effortHeavy5.1 million tokens
≈ 25 books · 2.9× typical

51 AI steps · 3 helpers involved · held up to ~300 pages in mind at once

  • Your conversations: 4.0 million
  • Helpers the AI started: 1.1 million across 3 sessions

Models used: claude-sonnet-5

4Fix the flaky login test and explain the root causeSep 10, 2026 · Codex · Team effortHeavy3.7 million tokens
≈ 19 books · 2.1× typical

47 AI steps · 6 helpers involved · held up to ~250 pages in mind at once

  • Your conversations: 3.3 million
  • Automatic safety checks: 480 thousand across 6 sessions

Models used: codex-auto-review, gpt-5.6-sol

5Plan the launch checklist for the new mobile app releaseSep 8, 2026 · Claude · Team effortTypical2.1 million tokens
≈ 10 books · 1.2× typical

36 AI steps · 4 helpers involved · held up to ~165 pages in mind at once

  • Your conversations: 927 thousand
  • Work handed to Codex: 680 thousand across 1 session
  • Helpers the AI started: 303 thousand across 1 session
  • Automatic safety checks: 166 thousand across 2 sessions

Models used: claude-sonnet-5, codex-auto-review, gpt-5.6-sol

6which one would you pick and whySep 12, 2026 · Claude · Multi-stepTypical1.8 million tokens
≈ 9 books · 1.0× typical

8 AI steps · 0 helpers involved · held up to ~346 pages in mind at once

  • Your conversations: 1.8 million

Models used: claude-sonnet-5

7shorter, and lead with the numbersSep 10, 2026 · Claude · Multi-stepTypical1.1 million tokens
≈ 1,598 pages · 0.6× typical

12 AI steps · 0 helpers involved · held up to ~153 pages in mind at once

  • Your conversations: 1.1 million

Models used: claude-sonnet-5

8Rename the internal config keys across the repoSep 13, 2026 · Codex · Multi-stepLight854 thousand tokens
≈ 1,280 pages · 0.5× typical

17 AI steps · 2 helpers involved · held up to ~116 pages in mind at once

  • Your conversations: 716 thousand
  • Automatic safety checks: 138 thousand across 2 sessions

Models used: codex-auto-review, gpt-5.6-sol

9Draft the quarterly board update from these notesSep 10, 2026 · Claude · Multi-stepLight825 thousand tokens
≈ 1,237 pages · 0.5× typical

16 AI steps · 0 helpers involved · held up to ~107 pages in mind at once

  • Your conversations: 825 thousand

Models used: claude-sonnet-5

10Summarise last week's customer support ticketsSep 8, 2026 · Claude · Multi-stepLight797 thousand tokens
≈ 1,195 pages · 0.5× typical

18 AI steps · 0 helpers involved · held up to ~94 pages in mind at once

  • Your conversations: 797 thousand

Models used: claude-sonnet-5

Show the top 25 as a table
#TaskTokensStepsHelpersSize
1yes please, go ahead with all of it18,055,8051007Very heavy
2add the rollout risks and owners8,017,290241Heavy
3Compare three vendors for the analytics migration5,055,508513Heavy
4Fix the flaky login test and explain the root cause3,744,206476Heavy
5Plan the launch checklist for the new mobile app release2,076,882364Typical
6which one would you pick and why1,771,36680Typical
7shorter, and lead with the numbers1,065,672120Typical
8Rename the internal config keys across the repo853,971172Light
9Draft the quarterly board update from these notes825,236160Light
10Summarise last week's customer support tickets797,347180Light
11Translate the onboarding email into Bahasa Indonesia97,17960Light

When were you busiest?

Tokens per day (M = million, B = billion). Days use your computer's clock.

010M20M30M40MBusiest day · 26.1 millionTue 8Wed 9Thu 10Fri 11Sat 12Sun 13Mon 14
Show as a table
DayTokensRoughly
Tue Sep 8, 20262,874,22914 books
Wed Sep 9, 202626,073,095130 books
Thu Sep 10, 20265,635,11428 books
Fri Sep 11, 20265,055,50825 books
Sat Sep 12, 20261,771,3669 books
Sun Sep 13, 2026853,9711,280 pages
Mon Sep 14, 202697,179146 pages

Which AI tools and models?

By tool

By model

What this page cannot see

Words used on this page

Token
A small piece of a word. Roughly 3 tokens is 2 words. About 667 tokens fill a page and 200,000 fill a 300-page book (rules of thumb, not exact).
Fresh reading / reused from memory
Each step, the AI re-reads the whole conversation so far. Providers remember part of it ("caching"), which is usually cheaper and faster than reading it new.
Helper, hand-off, safety check
Modern AI tools often start other AI sessions to do part of the job. Those sessions use tokens too, so they are counted with the task that caused them.
Light · Typical · Heavy · Very heavy · Extreme
Size compared with your own typical task (the median): under half is Light, up to 2× Typical, up to 5× Heavy, up to 20× Very heavy, beyond that Extreme.
Simple · Multi-step · Team effort
How complicated the job was: Simple is a handful of steps; Team effort means several helpers or 150+ steps.

Generated Sep 25, 2026 11:18. This file may contain snippets of your prompts — check before sharing it.