🔍 Read the full analysis: GitHub’s 4-In-10 AI Pull Request Trend Brings Review Into Focus on ThorstenMeyerAI.com
Get the latest gadgets delivered free with Prime
- Fast, free delivery on millions of items
- Prime Video, Amazon Music and more included
- Member-only deals all year
TL;DR
GitHub’s Octoverse 2026 report says more than 40% of pull requests on its platform in September started with a detectable coding agent, up from 17% in March. The company also introduced AI review and model-routing tools, while stating that developers remain accountable for shipped code.
More than 40% of GitHub pull requests in September 2026 started with a coding agent, up from 17% in March, according to the company’s Octoverse report released October 28. GitHub says the September total was 110 million agent-started pull requests; the figure measures detectable agent use, not whether the resulting code was correct or safe to merge.
GitHub defines an agent-started pull request as one whose first draft came from a coding agent it can detect. The company says the count is a floor because its systems may miss some agent use. Its methodology says the report generally includes public and private repositories, and GitHub does not provide a separate agent share for each.
The report says 90% of agent-started pull requests were merged within two weeks in September, compared with 83% in February. Pull requests without a detected agent remained at about 86%. Those are merge rates, not measures of code quality: a merged change may still require rework or later be reverted.
GitHub’s launches this week focused on review and routing. Copilot code review Max gathers reviews from several model providers into a combined review, while Copilot Fusion routes different tasks to models. GitHub also made Copilot review approvals count toward required approvals. Estimated average review costs are $0.25 for Lite, $1.50 for Balanced and $10 for Max, plus GitHub Actions minutes.
Infographic 01 · The agent share
Four in ten pull requests now start with an agent.
GitHub’s own telemetry, March to September 2026. The first draft comes from an agent; review and merge stay with people.
Merged within two weeks
Share of pull requests merged within 14 days
Merged fast is not the same as correct. GitHub publishes no revert or defect rate.
Bigger changes to review
Share of pull requests that change more than one file
More files per change means more for a reviewer to check.
What GitHub counts: an “agent-started pull request” is one “whose first draft came from a coding agent that we can detect.” Undetected agents are missing, so GitHub calls the figure a floor. Metrics cover public and private repositories unless noted.
Source: GitHub Octoverse 2026, 28 Oct 2026 (text, chart captions, glossary and methodology). All figures are GitHub’s own.
Powered by Thorsten Meyer AI
Review Capacity Becomes the Constraint
The figures point to a shift in where software teams may spend time: when an agent can produce a first draft quickly, reviewing, testing and deciding whether to merge can take a larger share of the work. GitHub’s new products reflect that pressure, but automated review adds cost and does not remove the need for people to assess changes.
For organizations, the practical question is not only how many pull requests agents create. Teams will need to account for reviewer time, review credits and Actions usage, and track outcomes such as rework, reversions and incidents. The report’s merge statistic alone does not show whether agent-written changes perform as well as human-written ones after shipping.
For developers, the change puts added weight on writing precise task instructions and reading diffs critically. Smaller starter tasks have often helped junior developers learn codebases; agent adoption may change who handles those tasks and how newcomers gain that experience. The report does not quantify that effect.
Products Worth Considering
Amazon Kindle Paperwhite (12th Generation, 2024), 16 GB, 7-inch Display, Jade
DJI Mic 3 Wireless Microphone System (2 Transmitters, 1 Receiver, Charging Case)
Amazon Kindle Scribe Colorsoft 64GB (1st Generation)
As an affiliate, we earn on qualifying purchases.
How GitHub Defines Agent Work
The Octoverse report is GitHub’s annual review of activity on its platform. The 2026 edition covers October 1, 2025, to September 30, 2026. GitHub’s wording varies across the report, including “agent-started,” “agent-generated” and “agent-authored.” Its definition focuses on the first draft, so a pull request still counts if a person later substantially edits it.
GitHub recalculated its 2024 and 2025 figures using updated definitions and reporting windows, so older Octoverse totals are not directly comparable. Across the platform, the company reports 1.3 billion merged pull requests during the 12 months to September, up from 538 million in 2025 and 402 million in 2024. Those platform-wide totals include more than agent-started work.
GitHub also reports that 87% of agent-started pull requests changed more than one file, compared with 79% of pull requests without a detected agent. That difference may add to the material reviewers must check, though the report does not establish how complexity or defect rates compare.
“A pull request whose first draft came from a coding agent that we can detect.”
— GitHub’s Octoverse report
What the Adoption Figure Cannot Show
GitHub does not disclose how many agent uses its detection misses, or how the 40%-plus share breaks down between public and private repositories. Because the measure is based on a detectable first draft, it also does not capture how much humans changed each pull request afterward.
The report’s merge rates do not establish whether agent-started code has comparable defect, security, maintenance or post-release incident rates. Nor does the supplied information show whether Copilot reviews catch problems that human reviewers miss or how frequently teams will use each paid review tier. GitHub says its cloud agent cannot approve or merge its own pull requests, and the person who requested a change cannot approve it, but the wider consequences of the new approval option remain unclear.
Teams Set Review and Approval Rules
GitHub has not announced a later measurement date for the agent-started share. The next evidence to watch for is whether future reports provide more detail on detection, repository types and code outcomes, rather than only adoption and merge rates.
Companies adopting the new tools will need to decide where Copilot approvals count, how many human approvals changes require, and how they will monitor review spending. The central test will be whether faster drafting is matched by reliable review and acceptable production outcomes. GitHub’s report does not yet answer that question.
Key Questions
What does GitHub mean by an agent-started pull request?
It is a pull request whose first draft came from a coding agent GitHub can detect. Human edits made afterward do not remove it from that category.
Did coding agents start more than 40% of all September pull requests?
GitHub says more than 40% of September pull requests started with a detectable agent. It calls the figure a floor because some agent activity may not be detected.
Does the 90% merge rate mean agent-written code was correct?
No. GitHub reports that 90% of agent-started pull requests were merged within two weeks in September. A merge rate does not establish correctness, security or performance after release.
How much does Copilot code review cost?
GitHub estimates an average review at $0.25 for Lite, $1.50 for Balanced and $10 for Max, plus GitHub Actions minutes.
Who is responsible for agent-written code that ships?
GitHub says developers remain accountable. Its cloud agent cannot approve or merge its own pull request, and the person who requested a change cannot approve it either.
Source: ThorstenMeyerAI.com
