Do these 3 things before closing this tab:
1Clear out junk files and repair common Windows errors2Scan for outdated or missing drivers - takes under a minute3Repair Windows errors before they cause bigger problemsiTechGuides is reader-supported. When you buy through links on our site, we may earn an affiliate commission. As an Amazon Associate I earn from qualifying purchases. Learn more
Azure DevOps does not have a documented native metric that counts AI-generated code volume. Microsoft documents tools for reviewing pull requests, tracking Copilot work from Azure Boards, and monitoring coding-agent activity—but those features measure different things. None establishes how many AI-generated lines were retained or merged.
What Azure DevOps documents for reviewing code
Copilot Code Review in Azure Repos
GitHub Copilot Code Review can review Azure Repos pull requests. Teams can enable it at the organization, project, or repository level, request a review manually, or configure branch policies to request one automatically. It comments on changed code and can offer suggestions. The review is always recorded as a Comment; it does not approve the pull request or satisfy a required-reviewer policy.
Azure DevOps records the person who requested the review and the selected effort level in pull-request activity. Those fields document review activity, not who authored the code or what share of a change came from AI. See Microsoft’s Copilot code review documentation.
Outdated Drivers Are Slowing You Down
One free scan finds every outdated or missing driver and matches the right update for your exact hardware.Free scan · exact hardware matchWindows Errors?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 reinstallDuring the documented preview, a pull request must be active and have no merge conflicts. Its repository must be 10 GB or smaller, and the pull request can contain no more than 100 changed files or 100 changes. Microsoft may change these preview limits; consult the troubleshooting guidance for current requirements.
#1 Best Overall
Microsoft’s 2026 sprint release notes identify Copilot Code Review for Azure Repos as a public-preview feature and describe tracking review costs by project through Azure Cost Management tags and budget alerts. Preview status, availability, cost, and limits can change, so confirm them before making the feature part of a required workflow. Microsoft’s 2026 sprint release notes
Copilot work launched from Azure Boards
A separate Azure Boards integration lets a user start GitHub Copilot from a work item. It can create a branch and draft pull request in a selected GitHub repository, link them to the work item, and show statuses such as In Progress, Ready for Review, and Error. This tracks workflow progress; it is not an Azure Repos code-volume report.
The repository requirement matters: Microsoft says this integration requires GitHub repositories and GitHub App authentication. Azure Repos Git repositories are not supported. Use GitHub Copilot with Azure Boards
What agent telemetry can tell you
For operational monitoring, Microsoft documents a Grafana pipeline that sends coding-agent telemetry over OTLP to an OpenTelemetry Collector, forwards it to Application Insights, and queries it through Azure Monitor and Log Analytics. The guide describes dashboards for token consumption, sessions, model usage, tool invocations, latency, errors, and costs. These signals help answer questions such as how much agents cost or which agents are being used; they do not count accepted AI-authored lines.
Rank #3
Tokens, sessions, review activity, and pull-request changes are not interchangeable with generated-code volume. A token count does not reveal how much code an agent produced, and a changed-line count does not identify which lines were AI-generated. Microsoft’s coding-agent observability guide documents agent activity and operations, not an accepted-code attribution metric.
How to define a useful AI-code volume metric
If a team needs a number, it must first decide what that number represents. Possible definitions include lines proposed by an AI tool, AI-proposed lines retained after human review, or AI-attributed lines in merged changes. These answer different questions and produce different totals.
- Proposed volume: count code generated by the tool before review. This requires capturing generated output and associating it with a pull request or work item.
- Retained volume: count generated lines that remain after review and editing. This requires comparing captured output with the reviewed version and defining how to handle rewrites and mixed authorship.
- Merged volume: count attributed lines that survive into the merged result. This requires preserving attribution through edits and merges, then defining treatment of deletions, moved code, and generated code assembled from multiple sources.
For any definition, document the counting unit, attribution method, time period, and whether the figure covers proposed, retained, or merged code. Add instrumentation that preserves an auditable link between the AI output and the resulting change. Without that, report observable proxies—such as pull-request size or agent tokens—as proxies, not as AI-generated code volume.
Data handling and governance
Microsoft’s Azure Repos FAQ says that 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 retention schedule for this feature. For current retention and processing details, consult Microsoft’s linked data-privacy information and the GitHub Copilot trust and privacy materials linked there. Confirm applicable terms with your organization’s administrator before enabling reviews. Microsoft’s Copilot code review FAQ
Quick Recap
Best Value
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.
