🔍 Read the full analysis: GitHub’s AI Agent Adoption Is Shifting Pull Request Work Toward Review on ThorstenMeyerAI.com
Get business pricing on tech for your team
- Business-only prices and quantity discounts
- Tax-exempt purchasing
- Multiple users, one account, clear invoices
TL;DR
GitHub’s Octoverse 2026 report says more than 40% of pull requests on the platform in September began with a coding agent’s first draft, up from 17% in March. The company’s new product releases focus on reviewing and routing agent-written changes, while GitHub says developers remain accountable for what ships.
More than 40% of pull requests on GitHub in September started with a coding agent’s first draft, up from 17% in March, according to the platform’s Octoverse 2026 report. The increase, which GitHub says represents 110 million agent-started pull requests in one month, coincides with new tools for reviewing and routing code.
GitHub defines an agent-started pull request as one whose first draft came from a coding agent it can detect. The company describes the resulting share as a floor because some agent use may not be detected. The measure includes public and private repositories, according to the report’s methodology, but GitHub did not provide a split between them. A pull request still counts as agent-started even if a developer later substantially edits the draft.
GitHub says 90% of agent pull requests were merged within two weeks in September, compared with 83% in February. For pull requests without a detected agent, the rate stayed at about 86%. Merging indicates that a change entered a codebase; it does not establish that the code was correct, safe or free of later problems.
The launches at GitHub Universe included Copilot code review Max, which uses several AI reviewers from different model providers and combines their feedback, and Copilot Fusion, a router that selects models for individual steps. GitHub also made Copilot review approvals eligible to count toward required approvals. Its estimated average review prices are $0.25 for Lite, $1.50 for Balanced and $10 for Max, with GitHub Actions minutes charged separately.
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 Becomes the New Bottleneck
When software agents produce more first drafts, developers may spend more time reading diffs, checking behavior and deciding whether to approve a change. This could affect how teams schedule reviewers and set release controls. GitHub’s figures describe volume and merge activity, not the quality of the resulting software.
The new review options add costs that organizations can compare with reviewer time. Companies may also decide whether an automated review can count toward a required approval. Measures such as rework, reverts and incidents could provide additional information about the effects of agent use; pull-request counts and merge rates alone do not measure software quality.
GitHub’s report identifies routine starter tasks as work agents can take on. It does not measure effects on hiring or training, so the implications for early-career work remain unclear.
Products Worth Considering
Logitech MX Mechanical Wireless Illuminated Keyboard Tactile (Graphite)
Bose SoundLink Flex (2nd Gen) Portable Bluetooth Speaker
LG 34GX90SA-W 34-inch Ultragear WQHD OLED Curved Gaming Monitor
As an affiliate, we earn on qualifying purchases.
How GitHub Counts Agent Work
Octoverse is GitHub’s annual report on activity across its platform. The 2026 edition covers October 1, 2025, through September 30, 2026. GitHub says developers pushed code 17.9 billion times during that period, while merged pull requests reached 1.3 billion, up from 402 million in 2024 and 538 million in 2025. The report says historical figures for 2024 and 2025 were recalculated using updated definitions and a different reporting window, so older editions are not directly comparable.
The report uses several related labels, including “agent-started,” “agent-generated” and “agent-authored.” Its clearest definition is based on whether a detectable agent supplied the first draft. GitHub says Copilot adoption is also shifting toward agent features: 55% of its monthly active users used them, compared with 35% a year earlier. Those figures describe GitHub’s platform and products; they do not establish adoption across the wider software industry.
“A pull request whose first draft came from a coding agent that we can detect.”
— GitHub, in its Octoverse 2026 methodology
What the Adoption Figures Cannot Show
The report does not say how many agent-started pull requests came from public repositories versus private company code, or how many agent contributions its detection method misses. The wording also varies across the report, making “agent-started” the most precise label for the 40%-plus figure. GitHub’s definition tracks the source of the first draft, not how much of the final change an agent wrote.
The figures do not establish whether agent-written code is more reliable, requires less total engineering time or leads to fewer defects. A high merge rate is not a quality measure, and GitHub did not provide a corresponding rate for reverts, incidents or rework in the material cited. It is also unclear how often organizations will allow Copilot approvals to satisfy their own review policies.
Teams Set Review and Approval Rules
GitHub’s newly announced review products give organizations options for routing and checking agent-generated changes. Organizations will determine how those tools fit into their release processes. Adoption of AI approvals, review costs compared with human review time, and software quality measures are among the factors that may be tracked as agent use changes.
GitHub’s report establishes a September platform snapshot, not a forecast. Data on defect rates, rework and the public-versus-private breakdown could provide more information about software outcomes and the volume of code entering review.
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. The label does not mean an agent necessarily wrote every line in the final change.
How many pull requests did agents start in September?
GitHub reported 110 million agent-started pull requests in September 2026, representing more than 40% of pull requests on the platform that month.
Does a high merge rate show that agent-written code is correct?
No. GitHub reported that 90% of agent pull requests were merged within two weeks, but a merge is not proof of correctness or safety. The cited figures do not provide defect or incident rates.
How much does GitHub estimate AI code review costs?
GitHub estimates an average review at $0.25 for Lite, $1.50 for Balanced and $10 for Max. GitHub Actions minutes are additional.
Who is responsible for code an agent helps write?
GitHub says developers remain accountable for what ships. It also says its cloud agent cannot approve or merge its own pull requests, and the person who requested a change cannot approve it.
Source: ThorstenMeyerAI.com
