- Dataset
- 2026-10-27-catalog-ai-v2
- Ruleset
- b2e8889c66f7
- Scanned
- 2026-10-27
- Window
- February–September 15, 2026
Prompty makes it easy to create, manage, debug, and evaluate LLM prompts for your AI applications. Prompty is an asset class and format for LLM prompts designed to enhance observability, understandability, and portability for developers.
01Result
microsoft/prompty ↗microsoft/prompty AI coding statistics: 90.9%
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 | 69.6% | 23 |
| 2026-03 | 98.5% | 68 |
| 2026-04 | 96.5% | 346 |
| 2026-05 | 100% | 23 |
| 2026-06 | 100% | 8 |
| 2026-07 | 60.9% | 46 |
| 2026-08 | 82.1% | 84 |
| 2026-09 | 85.7% | 28 |
Peak month: 100%. Bars are scaled to that peak, not to 100%.
Which agents
| Agent | Vendor | Commits | Share |
|---|---|---|---|
| GitHub Copilot | GitHub | 569 | 90.9% |
03Evidence
Inspect the matches
Public commit samples let you inspect the signatures behind the aggregate result.
Matched commit samples
1edd741don GitHubchore(rust): prepare 2.0.0 release (#545)GitHub Copilotc3831702on GitHubfix(release): use tag-separator key so release-please cuts slash tags (#54GitHub Copilot089167cfon GitHubfix(python): exempt strict-mode nonce from numeric coercion (#520) (#541)GitHub Copilot
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 | 693 |
| Merge commits removed | −43 |
| CI / dependency bots removed | −24 |
| Considered | 626 |
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/prompty