The AI Record
And so I started tracking the number of iterations, the number of review rounds between when the pull request was opened and when it was merged. Sure enough, very little difference. … Once again, very little if any statistical difference between human-generated and AI-generated pull requests in terms of how many iterations before they're ready to merge.

Daksh GuptaCo-founder · Executive, Greptile

Talk: AI-Generated Code Is Already Competing With Human Code, AI Engineer (YouTube), September 27, 2026, at 07:57.

Checked against the source [ Grade B ] Said in the last year Sells AI tools

Filed under

Who is speaking

Daksh Gupta, Co-founder. Analyzed Greptile's own pull request data (more than a million pull requests in some months) and runs the product he describes; an insider, though Greptile sells AI code review.

Greptile sells AI or agent tooling, so it has a reason to publish flattering numbers about AI. The passage stays in the archive; read it with that in mind.

How this was checked

Checked against the source by a first reader, then confirmed independently by a second reader who fetched the source without seeing the first reader's notes (Independent review agent (Claude Sonnet), blind second pass from passage text and citation only, no repository access, 2026-11-01).

Whisper at 07:57-08:19 matches. The ellipsis omits the garbled 'Devins, pr's, 2.1, codecs, pr's, 2.45, number of review cycles to merge, and humans right in the middle.'

How to cite this passage

Daksh Gupta (Greptile), “AI-Generated Code Is Already Competing With Human Code”, AI Engineer (YouTube), 2026-09-27, at 07:57. https://www.youtube.com/watch?v=474j-n1Ltxc Archived at https://the-ai-record.com/passages/greptile-very-little-difference-review-rounds-human-ai-prs-2026

More from the same source

You get a pretty high degree of confidence on merge. Today, almost a fifth of all the pull … are merged without any human review or without any human testing. … that is a number that we care a lot about and want to bring higher and higher, of course, within the guardrails of producing really high quality code.

Daksh GuptaCo-founder · Executive, Greptile

Talk: AI-Generated Code Is Already Competing With Human Code, AI Engineer (YouTube), September 27, 2026, at 11:50.

  • 20% share prs merged without human review, as of the talk (almost a fifth). No person in the loop

Checked against the source [ Grade B ] Said in the last year Sells AI tools Passage page

Today, … used by several tens of thousands of engineers every single week to review all of their code. So we also know, generally speaking, the number of pull requests that each of these people are writing. The median … user writes 50 pull requests a month, so call it about … per work day. The 90th percentile writes 500 pull requests per month. That is a drastic difference between the median and the P90. The P99 is in the thousands of pull requests.

Daksh GuptaCo-founder · Executive, Greptile

Talk: AI-Generated Code Is Already Competing With Human Code, AI Engineer (YouTube), September 27, 2026, at 10:00.

  • 50 prs median prs per user month, per month, as of the talk. Level not stated
  • 500 prs p90 prs per user month, per month, as of the talk. Level not stated

Checked against the source [ Grade B ] Said in the last year Sells AI tools Passage page

about a quarter of all the pull requests … in any given month were completely or at least largely generated by AI. Then I backtracked this data to the last 12 months. And it turns out that this number is growing really fast. In fact, early last year, fewer than 1% of pull requests had any evidence of being completely … generated.

Daksh GuptaCo-founder · Executive, Greptile

Talk: AI-Generated Code Is Already Competing With Human Code, AI Engineer (YouTube), September 27, 2026, at 04:36.

  • 25% share prs ai generated, any given month, as of the talk (about). Level not stated
  • 1% share prs ai generated, early last year (upper bound: 'fewer than 1%'). Level not stated

Checked against the source [ Grade B ] Said in the last year Sells AI tools Passage page

every time there's a pull request, we have a swarm of agents. And they go and look at every file that's changed, every file that's related to the files that change to figure out if there's bugs. And it also spins up your code in a sandbox, … dependencies, spins up local host, clicks around to try to break things, mocks inputs, and everything else to figure out if the code is broken.

Daksh GuptaCo-founder · Executive, Greptile

Talk: AI-Generated Code Is Already Competing With Human Code, AI Engineer (YouTube), September 27, 2026, at 00:27.

Checked against the source [ Grade B ] Said in the last year Sells AI tools Passage page

So then I started tracking the counts of P0s, P1s, and P2s in all of these changes. And interestingly, once again, there was not that much of a difference. In fact, three out of the four agents that we tested performed better than humans in terms of the rate at which … were producing P0s. They were producing fewer P0s than humans were. Similarly, the case with P1s and P2s. Broadly speaking, human-generated PRs were about equal in quality to … PRs based on this data.

Daksh GuptaCo-founder · Executive, Greptile

Talk: AI-Generated Code Is Already Competing With Human Code, AI Engineer (YouTube), September 27, 2026, at 07:07.

Checked against the source [ Grade B ] Said in the last year Sells AI tools Passage page

Something wrong? Report a correction. JSON: /api/v1/passages/greptile-very-little-difference-review-rounds-human-ai-prs-2026.json