The microsoft production-scale copilot study — 3.2 million users, 761 million llm calls, 95…
the microsoft production-scale copilot study — 3.2 million users, 761 million llm calls, 95 trillion tokens in one june week — found 87 percent of calls are now agent-initiated. the person at the keyboard is no longer the main caller of the model.
every interface decision after that point is just adapting to that fact.
Context
The arXiv paper 2608.00101, submitted 30 July 2026, analyzes sampled GitHub Copilot coding-agent traces: 13M sessions from over 3.2M users during a week in June 2026, with 761M LLM calls, 95T tokens and 775M tool invocations, and says 87% of LLM invocations are agent-initiated. A table caption says 13.5M sampled agent sessions.
The 87% is a share of LLM calls within these sampled coding-agent traces that the agent loop initiated, not user prompts. It covers GitHub Copilot's coding agent only, over a week in June 2026, so it is not all Copilot usage or all model usage. The traces are sampled and it is the authors' own study, not independent. Now means June 2026. The person at the keyboard is no longer the main caller is the author's interpretation. This is the same study as the earlier note on the Copilot traces.
Related work
- Earlier note on the same study ↗Same paper.
Watch next
- Peer review.
Sources
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 18 September 2026 at 16:51 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 →