This AI Assistant started as an internal experiment and now has scaled to support over 90% of PRs across the company impacting more than 600K pull requests per month.

Sneha TuliPrincipal Product Manager · Leader, Microsoft

Post: Enhancing Code Quality at Scale with AI-Powered Code Reviews, Engineering@Microsoft blog, July 14, 2025.

  • 90% prs covered share, as of July 2025 (post date). AI assists a person
  • 600,000 pull requests per month prs per month, as of July 2025 (post date). AI assists a person

Checked against the source [ Grade B ] One to two years old Microsoft: $332 billion revenue, FY2026 Sells AI tools

Filed under

Who is speaking

Sneha Tuli, Principal Product Manager. Leads the rollout of the pull request assistant she describes, so she is an insider; Microsoft sells AI tooling and the post ends by promoting GitHub Copilot, so it is promotional.

Microsoft sells AI or agent tools or services, so it has a reason to publish flattering numbers about AI. The passage stays in the archive; read it with that in mind.

How this was checked

Checked against the source by a first reader, then confirmed independently by a second reader who fetched the source without seeing the first reader's notes (Independent review agent (Claude Sonnet), blind second pass from passage text and citation only, no repository access, 2026-11-04).

Exact match. It is the intro paragraph of the post, authored by Sneha Tuli (byline and author box).

How to cite this passage

Sneha Tuli (Microsoft), “Enhancing Code Quality at Scale with AI-Powered Code Reviews”, Engineering@Microsoft blog, 2025-07-14. https://devblogs.microsoft.com/engineering-at-microsoft/enhancing-code-quality-at-scale-with-ai-powered-code-reviews/ Archived at https://the-ai-record.com/passages/microsoft-ai-assistant-started-internal-experiment-scaled-2025

More from the same source

Per early experiments and data science studies, 5000 repositories onboarded to AI code reviewer observed 10 – 20% median PR completion time improvements.

Sneha TuliPrincipal Product Manager · Leader, Microsoft

Post: Enhancing Code Quality at Scale with AI-Powered Code Reviews, Engineering@Microsoft blog, July 14, 2025, at Impact on quality and velocity.

  • 10% median pr completion time improvement low, early experiments, 5000 onboarded repositories. AI assists a person
  • 20% median pr completion time improvement high, early experiments, 5000 onboarded repositories. AI assists a person

Checked against the source [ Grade B ] One to two years old Microsoft: $332 billion revenue, FY2026 Sells AI tools Passage page

We have seen scenarios where PRs waited days and even weeks before getting merged, or where important feedback was missed. These pain points motivated us to try AI assistance in the review process. The goal was to let AI handle the repetitive or easily overlooked aspects of reviews, freeing human reviewers to focus on higher-level concerns.

Sneha TuliPrincipal Product Manager · Leader, Microsoft

Post: Enhancing Code Quality at Scale with AI-Powered Code Reviews, Engineering@Microsoft blog, July 14, 2025, at Solving the real problems in PR reviews with AI.

Checked against the source [ Grade B ] One to two years old Microsoft: $332 billion revenue, FY2026 Sells AI tools Passage page

When AI suggests code changes, it does not commit them directly. The author remains in control—reviewing, editing, and deciding whether to accept the suggestion by explicitly clicking ‘apply change’ option.

Sneha TuliPrincipal Product Manager · Leader, Microsoft

Post: Enhancing Code Quality at Scale with AI-Powered Code Reviews, Engineering@Microsoft blog, July 14, 2025, at Solving the real problems in PR reviews with AI.

Checked against the source [ Grade B ] One to two years old Microsoft: $332 billion revenue, FY2026 Sells AI tools Passage page

Teams across the company are leveraging these customizations to perform specialized reviews, like identifying regressions based on historical crash patterns or ensuring flight and change gates are in place.

Sneha TuliPrincipal Product Manager · Leader, Microsoft

Post: Enhancing Code Quality at Scale with AI-Powered Code Reviews, Engineering@Microsoft blog, July 14, 2025, at Customization: tailoring review for your team.

Checked against the source [ Grade B ] One to two years old Microsoft: $332 billion revenue, FY2026 Sells AI tools Passage page

Something wrong? Report a correction. JSON: /api/v1/passages/microsoft-ai-assistant-started-internal-experiment-scaled-2025.json