Source: https://internal-agents.com/agents/microsoft-prassistant # Microsoft — PRAssistant PRAssistant is Microsoft's internal AI code reviewer, built by its Developer Division Data and AI team. It joins each pull request as a reviewer, summarizes the change, and comments on specific lines with suggested edits the author applies. Microsoft says it shaped GitHub's Copilot code review. - Approach type: Background agent - Deployment stage: Scaled - Autonomy: Drafts reviewed - Evidence strength: Detailed primary - Status: Internal - First reported year: 2025 - Work: Code review - Interfaces: Github - Invocation: Event driven - Entry reviewed: 2026-09-15 ## Where people stay involved - **pull request → AI review comments** — Work product review · Level 3 ## Overview ### Summary PRAssistant is Microsoft's internal AI code reviewer, built by its Developer Division Data and AI team. It joins each pull request as a reviewer, summarizes the change, and comments on specific lines with suggested edits the author applies. Microsoft says it shaped GitHub's Copilot code review. Fact · Reported · High confidence · `microsoft-prassistant--summary` Confidence reason: A linked first-party source states the claim. Evidence: - Supports · [1] [Enhancing code quality at scale with AI-powered code reviews](https://devblogs.microsoft.com/engineering-at-microsoft/enhancing-code-quality-at-scale-with-ai-powered-code-reviews/) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/microsoft-prassistant-source-1/content.md) ## Supervision evidence ### Operating model assessment Level 3 for pull request → AI review comments; human attention boundary: work-product-review. Inference · Catalog judgment · Medium confidence · `microsoft-prassistant--operating-models-0` Confidence reason: The engineering blog describes engineers acting on PRAssistant review comments, which locates human attention at work-product review. Qualifications: - Observation date: 2025-07 Evidence: - Supports · [1] [Enhancing code quality at scale with AI-powered code reviews](https://devblogs.microsoft.com/engineering-at-microsoft/enhancing-code-quality-at-scale-with-ai-powered-code-reviews/) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/microsoft-prassistant-source-1/content.md) ## Implementation details ### Interfaces github Fact · Reported · High confidence · `microsoft-prassistant--architecture-interfaces` Confidence reason: A linked first-party source states the claim. Evidence: - Supports · [1] [Enhancing code quality at scale with AI-powered code reviews](https://devblogs.microsoft.com/engineering-at-microsoft/enhancing-code-quality-at-scale-with-ai-powered-code-reviews/) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/microsoft-prassistant-source-1/content.md) ## Reported metrics ### Headline claim Supports more than 90% of Microsoft PRs, impacting over 600,000 pull requests per month Metric · Reported · Medium confidence · `microsoft-prassistant--headline-metric` Confidence reason: Microsoft reported the figures in its own engineering blog without independent verification. Qualifications: - Reported by: Microsoft - Scope: PRs supported by the internal AI review assistant across Microsoft - Denominator: Company pull requests for coverage share - Observation date: 2025-07 Evidence: - Supports · [1] [Enhancing code quality at scale with AI-powered code reviews](https://devblogs.microsoft.com/engineering-at-microsoft/enhancing-code-quality-at-scale-with-ai-powered-code-reviews/) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/microsoft-prassistant-source-1/content.md) · Preserved content.md, lines 10 ### Key observation More than 90% of pull requests across the company Metric · Reported · Medium confidence · `microsoft-prassistant--key-metrics-0` Confidence reason: Microsoft reported the figures in its own engineering blog. Qualifications: - Reported by: Microsoft - Scope: PRs supported by the internal AI review assistant across Microsoft - Denominator: Company pull requests for coverage share Evidence: - Supports · [1] [Enhancing code quality at scale with AI-powered code reviews](https://devblogs.microsoft.com/engineering-at-microsoft/enhancing-code-quality-at-scale-with-ai-powered-code-reviews/) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/microsoft-prassistant-source-1/content.md) · Preserved content.md, lines 10 ### Key observation More than 600,000 pull requests impacted per month Metric · Reported · Medium confidence · `microsoft-prassistant--key-metrics-1` Confidence reason: Microsoft reported the figures in its own engineering blog. Qualifications: - Reported by: Microsoft - Scope: PRs supported by the internal AI review assistant across Microsoft - Denominator: Company pull requests for coverage share Evidence: - Supports · [1] [Enhancing code quality at scale with AI-powered code reviews](https://devblogs.microsoft.com/engineering-at-microsoft/enhancing-code-quality-at-scale-with-ai-powered-code-reviews/) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/microsoft-prassistant-source-1/content.md) · Preserved content.md, lines 10 ### Key observation About 5,000 repositories in early onboarding Metric · Reported · Medium confidence · `microsoft-prassistant--key-metrics-2` Confidence reason: Microsoft reported the figures in its own engineering blog. Qualifications: - The source does not report the denominator of this figure. - Reported by: Microsoft - Scope: Repositories onboarded in early AI code-review experiments - Method: Early experiments and data science studies across onboarded repositories Evidence: - Supports · [1] [Enhancing code quality at scale with AI-powered code reviews](https://devblogs.microsoft.com/engineering-at-microsoft/enhancing-code-quality-at-scale-with-ai-powered-code-reviews/) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/microsoft-prassistant-source-1/content.md) · Preserved content.md, lines 35 ## Sources 1. [Enhancing code quality at scale with AI-powered code reviews](https://devblogs.microsoft.com/engineering-at-microsoft/enhancing-code-quality-at-scale-with-ai-powered-code-reviews/) - Engineering blog · First party · Evidence - Original URL: - Published: 2025-07-14 · Accessed: 2026-08-13 · Last verified: 2026-08-31 - Preserved copy in the repository: