- Dataset
- 2026-10-27-catalog-ai-v2
- Ruleset
- b2e8889c66f7
- Scanned
- 2026-10-27
- Window
- February–September 15, 2026
Python version of the Playwright testing and automation library.
01Result
microsoft/playwright-python ↗microsoft/playwright-python AI coding statistics: 34.1%
One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.
02Drivers
What shapes this result
Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.
Assisted or autonomous
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
| Month | Agent share | Considered commits |
|---|---|---|
| 2026-02 | 0% | 1 |
| 2026-04 | 42.9% | 7 |
| 2026-05 | 25% | 8 |
| 2026-06 | 44.4% | 9 |
| 2026-07 | 28.6% | 7 |
| 2026-08 | 60% | 5 |
| 2026-09 | 0% | 4 |
Peak month: 60%. Bars are scaled to that peak, not to 100%.
Which agents
| Agent | Vendor | Commits | Share |
|---|---|---|---|
| GitHub Copilot | GitHub | 13 | 31.7% |
| Claude Code | Anthropic | 1 | 2.4% |
03Evidence
Inspect the matches
Public commit samples let you inspect the signatures behind the aggregate result.
Matched commit samples
154f67ceon GitHubfix(sync): wait for initialize before leaving __enter__ (#3168)GitHub Copilot4af2fc65on GitHubchore: roll Playwright to 1.62.1 (#3169)GitHub Copilot4d2e058fon GitHubfix(connection): register protocol callback only after successful send (#3GitHub Copilot581316cbon GitHubchore: roll to 1.59.1 (#3050)Claude Code
04Method
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 window | 76 |
| Merge commits removed | −0 |
| CI / dependency bots removed | −35 |
| Considered | 41 |
Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.
Continue exploring
Related coding-agent evidence
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 microsoft/playwright-python