🔍 Read the full analysis: Pull Request Review Takes On New Importance As AI Agents Join GitHub 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 2026 Octoverse report says more than 40% of pull requests on its platform in September began with a detectable coding agent, up from 17% in March. The company introduced AI review and model-routing tools as agent-written changes increase the volume of work people must assess; its figures measure starts and merges, not code quality.
More than 40% of GitHub pull requests in September began with a first draft from a coding agent the company could detect, up from 17% in March, according to GitHub’s Octoverse report released October 28. The shift is putting more weight on reviewing proposed code, and GitHub announced new tools for AI-assisted review, model selection and approval alongside the report.
GitHub says the September share represents 110 million agent-started pull requests, about six times March’s volume. Its definition counts a pull request when its first draft came from a coding agent GitHub can detect. The company describes the figure as a floor because some agent use may go undetected. The metric includes public and private repositories, and GitHub did not provide a split between them.
The company also reported that 90% of detected agent pull requests were merged within two weeks in September, compared with 83% in February. Pull requests without a detected agent held at about 86%. A merge indicates that a proposed change entered a codebase; it does not establish that the code was correct, safe or free of later rework.
GitHub introduced Copilot code review Max, which draws on several AI reviewers from different model providers and combines their reviews, and Copilot Fusion, a system that routes steps to models. It also said Copilot review can count toward required approvals. GitHub estimates an average review costs $0.25 for Lite, $1.50 for Balanced and $10 for Max, in addition to 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
When agents make it faster to produce a first draft, the work does not disappear; more of it shifts to checking changes, tracing their effects and deciding whether they should ship. That changes the practical bottleneck for teams: reviewer time and approval capacity may become as important to planning as coding time.
The reported merge rate should not be read as a quality score. GitHub’s figures do not show how often agent-written changes needed substantial revision, were reverted, or caused production problems. Teams weighing wider agent use will need to track those outcomes alongside pull-request volume and speed. The stated review prices also make the cost of automated review a budget question, not just a software feature.
GitHub says developers remain accountable for shipped code. It says its cloud agent cannot approve or merge its own pull requests, and the person who requested a change cannot approve it either. Those controls preserve a human sign-off step, while leaving organizations to decide when an AI review can count toward their own requirements.
Products Worth Considering
Logitech MX Mechanical Wireless Illuminated Keyboard Tactile (Graphite)
LG UltraGear 27-Inch QHD OLED Gaming Monitor, 240Hz, 0.03ms, G-SYNC Compatible, FreeSync Premium Pro, HDMI 2.1
Samsung 27-Inch Odyssey QD-OLED G8 4K 240Hz Gaming Monitor
As an affiliate, we earn on qualifying purchases.
How GitHub Defines Agent Starts
The Octoverse report covers October 1, 2025, through September 30, 2026, and summarizes activity on GitHub. The company recalculated its 2024 and 2025 figures under updated definitions and reporting windows, so older Octoverse totals are not directly comparable with the revised series.
GitHub’s wording varies across the report: it describes the measure as agent-started, agent-generated, agent-authored and agent-opened pull requests. Its definition is narrower and more useful for interpreting the headline: a request counts when its first draft came from an agent GitHub detects, even if a person later rewrites parts of it. The company’s data does not identify what share of those changes was substantially edited by humans.
The report describes wider growth in platform activity, including 1.3 billion merged pull requests over the year, up from 538 million in 2025. GitHub also says 55% of Copilot monthly active users use agent features, compared with 35% a year earlier. These figures provide platform context, but do not independently show whether agent use caused the increase in code activity.
“A pull request whose first draft came from a coding agent that we can detect.”
— GitHub, in its Octoverse methodology
What the Metrics Cannot Show
GitHub has not published an open-source versus private-repository breakdown for the 40%-plus figure, or a count of agent use its detection misses. Its report also does not show how much human editing typically follows an agent’s first draft. The number therefore measures detected agent starts, not the share of final code written by agents.
The reported merge rates do not establish whether merged changes were correct or how they performed after release. The source material provides no corresponding figures for rework, reverts or incidents across agent and non-agent pull requests. It is also not clear how widely companies will allow Copilot reviews to satisfy required approvals, or what their total review costs will be once usage and Actions minutes are included.
How Teams Measure Review Outcomes
GitHub’s report and product announcements put the next test inside engineering teams: whether AI review can keep up with the volume of agent-written proposals without weakening checks. Companies will have to set policies for when AI approval counts, retain human responsibility for changes that ship, and budget for review credits and compute-related charges.
For developers, the shift puts more emphasis on specifying tasks clearly and scrutinizing diffs rather than treating a successful merge as proof of correctness. The key evidence to watch is not only whether agents open and merge more pull requests, but whether changes need less or more rework and how often they lead to problems after release. GitHub has published the platform-level adoption figures; those quality and outcome comparisons remain unanswered.
Key Questions
What does GitHub mean by an agent-started pull request?
GitHub counts a pull request when its first draft came from a coding agent it can detect. A person may edit the draft afterward and it still counts under that definition.
Did agents start more than 40% of all code changes?
No. The figure refers to pull requests on GitHub in September 2026, not all code changes or all final code. GitHub says its detection may miss some agent use.
Does the merge rate prove agent-written code is reliable?
No. GitHub reported that 90% of detected agent pull requests merged within two weeks in September, but merging is not a measure of correctness. The report does not provide matching rework, revert or incident rates.
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. Actual organizational costs will depend on use.
Can GitHub’s cloud agent approve its own pull request?
GitHub says its cloud agent cannot approve or merge its own pull requests. It also says the person who requested the change cannot approve it.
Source: ThorstenMeyerAI.com
