FORTUNE-OS / ENGINEERING STORIES
Humans & machines.
The work we share, with the evidence behind it.
LATITUDE / LAST 24 HOURS
Explore model telemetry Beyond the commit trail.
Captured traces315Engineering trace cohort
Reported tokens1.7BTrace usage, separate from Entire
Estimated model cost$1,803.29USD · telemetry estimate
13K tool calls captured
MODEL SPANSUnreported model13.8Kclaude-opus-5-511.3Kclaude-sonnet-5-5626
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
3Accepted PRs with known Fortune identityAI-assisted PRs
3Entire or explicit coauthor evidenceCheckpoints available
16/16Unique checkpoints in selected commitsReported output tokens
472.6KEntire checkpoint reports; not a billA SHARED MANIFEST
Who helped this ship?
100%
of accepted, non-dependency PRs have known agent involvement.
Autopilot3
AI-assisted3
No known attribution0
Dependency automation0
Missing attribution is unknown. It does not mean “written entirely by a human”.
CAPTURED EVIDENCE
Inside the machine room
Input tokens307.6K
Cache read tokens102.2M
Cache write tokens1.9M
Line attribution samples15
Reported agent lines870
Estimated model costView Latitude
claude-opus-5-5claude-opus-5gpt-6-astra
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 | 3 | 4 | 166 | 6 | ||
| 02 | 0 | 8 | 0 | — |
FROM THE ACTUAL RUN LEDGER
Agent operations
3runs started
3runs with a PR
0human decision gates
24.9mmedian run duration
completed3
6240 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.