What’s actually slowing this PC down?
Pick the symptom - the matching free tool is one click away.
Microsoft’s documented Azure DevOps features do not provide a native metric for how much code AI generated, how much a developer retained, or how much of it was ultimately merged. Azure Repos can use GitHub Copilot Code Review to review pull requests, while separate tools can track work-item progress or agent activity. Those signals are useful, but they measure different things.
What Azure DevOps can—and cannot—tell you
The answer depends on what you mean by “reviewing” AI-generated code. Microsoft documents three relevant capabilities: Copilot Code Review for Azure Repos pull requests, a GitHub Copilot workflow launched from Azure Boards, and telemetry dashboards for coding-agent activity. None is documented as a counter for AI-authored lines.
As an Amazon Associate I earn from qualifying purchases.
| Capability | Repository or data source | What it records or shows | What it does not establish |
|---|---|---|---|
| Copilot Code Review | Azure Repos | Review comments and suggestions on changed code; pull-request activity records the requester and selected effort level. | Which lines were AI-authored, retained after human edits, or merged. |
| Copilot from Azure Boards | GitHub repositories | Work-item-linked branch and draft pull request, with workflow statuses such as In Progress, Ready for Review, and Error. | AI-generated code volume. Azure Repos repositories are not supported by this integration. |
| Agent observability | Agent telemetry sent through an OpenTelemetry pipeline | Signals such as tokens, sessions, model usage, tool calls, latency, errors, and costs. | Accepted or merged AI-generated lines. |
Do not treat changed lines, review counts, tokens, or sessions as interchangeable measures of AI-generated volume. Each describes a different part of a development workflow.
Outdated Drivers Are Slowing You Down
One free scan finds every outdated or missing driver and matches the right update for your exact hardware.Free scan · exact hardware matchWindows Errors? Fix Them Before They Spread
Repair common Windows errors and clear accumulated junk for a smoother, more stable PC - no reinstall needed.Free scan · no reinstallReviewing pull requests in Azure Repos
Microsoft documents Copilot Code Review for Azure Repos as a pull-request reviewer. An organization can enable it at the organization, project, or repository level. A team can request a review manually or configure branch policies to request one automatically. The reviewer comments on changed lines and can offer suggestions. Microsoft says Azure DevOps records the requester and effort level in pull-request activity; that activity is about the review request, not authorship of the code.
#1 Best Overall
The review always leaves a Comment review. It does not approve the pull request or satisfy a required-reviewer policy, so teams should retain their normal approval rules and human review responsibilities. Microsoft’s Copilot code review guide describes setup and behavior.
Preview eligibility and limits
Microsoft’s troubleshooting documentation lists these conditions for the public preview:
- The pull request must be active and have no merge conflicts.
- The repository must be 10 GB or smaller.
- The pull request can contain no more than 100 changed files or 100 changes.
These are preview limits and may change. Check the current documentation before designing a process around them. Microsoft’s troubleshooting guide covers eligibility and common issues.
Microsoft’s 2026 sprint release notes describe Copilot Code Review for Azure Repos as a public preview for Azure DevOps customers. They also say review costs can be tracked by project using Azure Cost Management tags and budget alerts. Cost tracking helps with spend oversight; it does not convert review activity into a code-volume measure. See the Sprint 271 release notes for the release context.
Rank #3
Why the Azure Boards coding workflow is different
Microsoft also documents starting GitHub Copilot from an Azure Boards work item. The workflow can create a branch and draft pull request in a selected GitHub repository, link them to the work item, and display progress statuses. It is a way to connect work tracking with a GitHub-based coding workflow—not a code-generation feature inside Azure Repos.
The repository limitation is explicit: the integration requires GitHub repositories and GitHub App authentication; Azure Repos Git repositories are not supported. Do not use this integration’s linked work items or status changes as evidence of AI-generated code volume. Microsoft explains the workflow and its requirements in Use GitHub Copilot with Azure Boards.
What agent telemetry can measure
For operational monitoring, Microsoft documents a coding-agent observability pipeline: agents send OpenTelemetry data over OTLP to an OpenTelemetry Collector, which forwards it to Application Insights. Grafana dashboards then query the data through Azure Monitor and Log Analytics. The guide covers signals including token consumption, sessions, model usage, tool invocations, latency, errors, and costs.
Free tools Windows power users keep installed
One-click scans. No signup required.
These signals can help answer questions such as how much agents are being used, which models or tools are involved, and where errors or costs occur. They do not show how many generated lines survived review or reached a merge. A session or token count is usage telemetry, not an authorship audit. The pipeline and dashboard examples are in Microsoft’s coding-agent observability guide.
Best Value
Define the volume metric before reporting a number
If your team needs an AI-generated-code-volume figure, first decide what the numerator represents. Possible definitions include generated lines proposed, generated lines retained after review, or AI-attributed lines merged. These answer different questions, so a report should name its definition rather than label a general change-size or usage figure “AI-generated code.”
- Proposed: Count code initially produced by an AI tool, including code later edited or discarded. This requires capturing an attributable generation artifact or equivalent record.
- Retained: Count AI-originated code remaining after review and human edits. This requires a way to preserve attribution through those edits.
- Merged: Count attributed code that is present in the merged result. This requires linking generation provenance to the reviewed and merged change.
For any definition, specify the unit and scope—for example, lines or changed files, a repository or team, and a reporting period—and explain how edits, deletions, generated tests, and copied code are treated. Keep the underlying records auditable. Pull-request size can be a change-size proxy, and tokens or sessions can be usage proxies, but neither alone proves AI authorship or acceptance.
Privacy and governance considerations
Microsoft’s Azure Repos FAQ says Copilot Code Review interaction data—including pull-request diffs, prompts, responses, suggestions, and related review context—is not used to train or improve foundation models. The FAQ does not publish a separate feature-specific retention schedule for Azure Repos; it directs readers to GitHub Copilot trust and privacy information for current retention and processing details. Review those terms alongside your organization’s data-handling requirements before enabling the feature. See Microsoft’s Copilot code review FAQ.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
