Enterprise agents are finally getting an expense report. claude's smart reports beta, out september…
enterprise agents are finally getting an expense report. claude's smart reports beta, out september 10 on enterprise plans, tracks what sessions actually do, what they cost, where they hit friction, and which repeated patterns deserve to become shared skills.
usage analytics just became a code generation input.
Context
Anthropic's help article on smart reports says they analyze how a team uses Claude and report on the work done, what it costs, where sessions hit friction and which repeated patterns are worth packaging as shared skills. They are in beta on Claude Enterprise plans, not available to organizations with CMEK or HIPAA configurations, and an admin chooses the scope, up to the last 28 days. Claude reads a sample of transcripts and groups them into workstreams with spend attached, there is a limit of 10 free reports per organization per month in beta, and restricted or personal sessions are aggregate only.
It reads a sample of transcripts and not every session, so tracks what sessions do overstates it. The 10 September launch date comes from secondary tracker snippets and the help article carries no beta start date. Code generation input is the author's idea and not a described feature. A beta, with admin and privacy limits.
Claude Code's analytics docs describe counter-based usage and contribution metrics (lines accepted, accept rate, daily active users, sessions, a leaderboard and export), with spend tracking in the Console. Smart reports differ in scope: they read a sample of transcripts across chat, Claude Code and Cowork to group workstreams, attach spend, list frictions and suggest shared skills. The expense report fits the spend-by-workstream view, and the friction and skill parts are not covered by the metric dashboards.
Related work
- Claude Code analytics (Claude Code docs) ↗Counter-based analytics for Claude Code.
Watch next
- Smart reports leaving beta and the admin controls.
Sources
- Get started with smart reports (Claude Help)support.claude.com
- Claude Code analytics (Claude Code docs)code.claude.com
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 20 September 2026 at 10:43 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →