FORTUNE-OS / ENGINEERING STORIES
Humans & machines.
The work we share, with the evidence behind it.
LAST 90 DAYS
LATITUDE / LAST 90 DAYS
Explore model telemetry Beyond the commit trail.
Captured traces7,362Engineering trace cohort
Reported tokens47.1BTrace usage, separate from Entire
Estimated model cost$48.98KUSD · telemetry estimate
224.9K tool calls captured
MODEL SPANSUnreported model242.2Kclaude-opus-5-5137.1Kclaude-opus-575.7K
Whole engineering project; district filters do not narrow these counts. Business agents are separate in the Observatory. Trace tokens, checkpoint reports and tool cohorts are not added together; estimated cost is not a provider invoice.
Autopilot participation
50Accepted PRs with known Fortune identityAI-assisted PRs
29Entire or explicit coauthor evidenceCheckpoints available
339/383Unique checkpoints in selected commitsReported output tokens
40.3MEntire checkpoint reports; not a billA SHARED MANIFEST
Who helped this ship?
91%
of accepted, non-dependency PRs have known agent involvement.
Autopilot50
AI-assisted29
No known attribution8
Dependency automation6
Missing attribution is unknown. It does not mean “written entirely by a human”.
CAPTURED EVIDENCE
Inside the machine room
Input tokens106.2M
Cache read tokens19.7B
Cache write tokens188.8M
Line attribution samples282
Reported agent lines32.5K
Estimated model costView Latitude
claude-opus-5-5claude-opus-5claude-opus-5-5[1m]claude-sonnet-5-5gpt-6-astraclaude-opus-5[1m]claude-fable-5-1claude-fable-5claude-sonnet-5
PR involvement, token usage and line attribution measure different things. Coverage and metric versions constrain comparisons.
The human + machine league
| # | CREW MEMBER | MERGED | REVIEWS | LINES − | AI-LINKED PRs | |
|---|---|---|---|---|---|---|
| 01 |  Anton Vinogradov@awinogradov | 26 | 53 | 61K | 40 | |
| 02 |  dsuranov@dsuranov | 4 | 30 | 2,403 | 31 | |
| 03 |  Anton Kostenko@soulko | 3 | 7 | 250 | 5 | |
| 04 |  Vladimir Kuzmin@garvae | 0 | 0 | 0 | 1 | |
| 04 |  Olga Venger@olga-venger | 0 | 0 | 0 | 1 | |
| 06 |  Fortis AI@fortis-bot | 3 | 0 | 7 | — | |
| 06 |  fortune-reviewer@fortune-reviewer | 0 | 225 | 0 | — | |
| 06 |  Arthur Kozulia@rovnyart | 0 | 2 | 0 | — |
FROM THE ACTUAL RUN LEDGER
Agent operations
59runs started
59runs with a PR
0human decision gates
57.1mmedian run duration
completed56
failed2
waiting_effect1
6241 metadata-only runs, joined to delivered PRs. Separate column-scoped read-only database role; prompts and run specifications excluded. A run, a PR and an accepted delivery remain separate counts.