Microsoft's telemetry on copilot's agentic coding
microsoft's telemetry on copilot's agentic coding: 3.2 million users, 13 million sessions, and 761 million llm calls in a single june week. that's not a pilot; that's a runtime.
the agent workload just became the biggest api consumer most companies will ever run.
Context
An arXiv paper submitted 30 July 2026, Agentic Coding in the Wild: Characterizing GitHub Copilot Traces at Production Scale, reports sampled GitHub Copilot traces from June 2026 comprising 3.2M users, 13M sessions, 761M LLM calls and 95T tokens.
These are the authors' own figures, not independently audited. The abstract says sampled traces from June 2026, not a single week, and the window length and the definition of a session are in the full text, which was not read. Because the traces are sampled, the totals are not all Copilot usage. That it is a runtime and the biggest API consumer are the author's opinion.
Related work
- Agentic coding in the wild (Microsoft Research) ↗Snippet only.
Watch next
- The full paper for the sampling window and the session definition.
Sources
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 18 September 2026 at 10:09 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 →