Pulse
2026-09-18-v3.0
Dataset
2026-10-27-catalog-ai-v2
Ruleset
b2e8889c66f7
Scanned
2026-10-27
Window
February–September 15, 2026
Catalog tracking observation. This repository is measured with the same fixed window and ruleset, but it is not part of the published benchmark or its aggregate claims.

Open source documentation of Microsoft Azure

MicrosoftDocs/azure-docs ↗

MicrosoftDocs/azure-docs AI coding statistics: 5.5%

of 18,113 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
5.5% agent · top contributor 11.8%170 contributors
org-wide

Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.

992
agent commits
17,121
other considered commits
170
agent contributors
11.8%
largest contributor

What shapes this result

Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.

Assisted or autonomous

919assisted
73autonomous

Assisted — a developer’s identity authored the commit and the agent added itself as co-author. Autonomous — a bot identity authored the commit without a human identity attached.

Agent share by month

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-010%6
2026-022.4%3271
2026-032.4%3788
2026-046.3%3074
2026-056.1%2510
2026-064.9%1555
2026-076.5%1909
2026-0814.7%1493
2026-0910.8%507

Peak month: 14.7%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
GitHub CopilotGitHub9865.4%
Claude CodeAnthropic60%

Inspect the matches

Public commit samples let you inspect the signatures behind the aggregate result.

Matched commit samples

What entered the denominator

The result begins with commit history, removes merges and routine automation, and reports literal agent signatures as a lower bound.

Exclusion ledger

Commits in window27,175
Merge commits removed−9,041
CI / dependency bots removed−21
Considered18,113

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

Reproduce this observation

Run the same detector locally.

Deterministic signature matching; no code-style inference. Squash merges can remove trailers, so this result remains a measured floor.

npx qmmit-cli MicrosoftDocs/azure-docs

Scan another repository