# Don’t get one-shotted: Use AI to test, review, merge, and deploy code — Tomas Reimers, Graphite AI Engineer · 2025-06-27 Tomas Reimers, CPO and co-founder of Graphite, argues that AI-generated code accelerates the inner loop (development) but bottlenecks the outer loop (review, test, merge, deploy), necessitating AI-native tooling across the entire workflow. He presents Graphite's AI code reviewer, Diamond, which achieves a 52% acceptance rate on its comments—exceeding the 45–50% rate for human comments—while only 4% of its comments are dismissed. Reimers emphasizes that AI tools must deeply understand the codebase, integrate with CI/testing pipelines, and provide high-signal, low-noise feedback to handle the increasing volume of AI-assisted code. He cites that 46% of GitHub code is now written by Copilot, and predicts the outer loop will break without AI-driven prioritization, review automation, and optimized deployment. The talk advocates for self-driving code review that lets developers focus on product features rather than manual processes. ## Questions this episode answers ### What percentage of code on GitHub is being written by AI, according to the GitHub Developer Survey cited by Graphite's co-founder? According to the GitHub Developer Survey cited by Tomas Reimers, co-founder of Graphite, 46% of code on GitHub is being written by Copilot. He also noted that nearly every developer surveyed used AI tools both inside and outside of work, highlighting the rapid adoption of AI in the inner loop of software development. [0:49](https://aie.addtry.com/c283f438-37a8-4486-8d0a-65962b8109ca?t=49000) ### How is Graphite addressing the bottleneck in code review caused by increased AI code generation? Tomas Reimers explains that as AI tools like Cursor and Copilot accelerate the inner loop of development, the outer loop—testing, reviewing, merging, deploying—becomes the bottleneck. Graphite’s solution is to build AI-native toolchains, like their AI code reviewer Diamond, which deeply understands the codebase, summarizes changes, and integrates with CI/testing to streamline review, helping teams handle higher code volumes without sacrificing quality. [1:27](https://aie.addtry.com/c283f438-37a8-4486-8d0a-65962b8109ca?t=87000) ### How does the acceptance rate of AI code review comments from Graphite's Diamond compare to human comments? Tomas Reimers reports that Diamond's comments are accepted at a higher rate than human comments. Human comments are integrated into pull requests about 45–50% of the time, while Diamond's comments are accepted 52% of the time. Additionally, Diamond's comments are dismissed at a rate of less than 4%, indicating high signal and low noise. These figures are based on Graphite's internal tuning as of March. [5:08](https://aie.addtry.com/c283f438-37a8-4486-8d0a-65962b8109ca?t=308000) ## Key moments - **[0:00] Two Loops** - [0:00] Software development has two loops: the inner loop for development and the outer loop for review, explains Tomas Reimers. - [0:01] 46% of code on GitHub is being written by Copilot, according to a GitHub Developer Survey cited by Tomas Reimers. - [0:03] "The problems are being created by AI, they can also probably be solved by AI," says Tomas Reimers. - [0:04] "Your entire toolchain has to be AI-native, not just your IDE," says Tomas Reimers. - [0:04] Graphite's AI code review comments are accepted at 52%, higher than the 45-50% acceptance rate of human comments, reports Tomas Reimers. - **[0:49] AI Surge** - **[1:27] Review Bottleneck** - **[3:19] AI-Native Solution** - **[4:18] Diamond Platform** ## Speakers - **Tomas Reimers** (guest) ## Topics Developer Productivity ## Mentioned Graphite (company), Bolt (product), Copilot (product), Cursor (product), Diamond (product), Windsurf (product), v0 (product) ## Transcript ### Two Loops **Tomas Reimers** [0:15] Awesome. Uh, hi everyone. My name is Tomas, I'm one of the co-founders of Graphite. Graphite is an AI code review, uh, company. So, to give some context on sort of where we see the industryright now and where we see it going: software development currently, and has always had, two loops. The inner loop, which is focused on development, and the outer loop that's focused on review. Developers spend time in the inner loop, they get their code working, they get the feature the way they want it, and then they go ahead and they move it to the outer loop where it's tested, reviewed, merged, deployed. We're seeing the inner loop changeright now more than we've ever seen it. More developers are using AI than ever. I thinkright here we have some statistics from the GitHub Developer Survey. Nearly every developer surveyed used AI tools both inside and outside of work, and 46% of GitHub is being written by co-pa, uh, of code on GitHub is being written by Copilot. ### AI Surge **Tomas Reimers** [1:07] We're seeing more and more code being written by AI. Here we have some statistics around how code has changed over time and how some people predict it will change. And even if we take a more pessimistic view of that, we still see the way the world's going as just more and more and more code being written by AI. The inner loop is changing, you know? AI is making more, uh, developers more productive. Developers are now producing higher volumes of code, but that code still needs to be reviewed. When we first started looking at this, when we first started building, uh, Diamond, our AI code reviewer, about a year ago now, what we found was we read a lot of articles that scared us a lot. ### Review Bottleneck **Tomas Reimers** [1:48] We were seeing within our own organization a lot of developers adopting AI tools, but we were also seeing a problem: AI can hallucinate, it can make mistakes, and almost more scarily, it can make security vulnerabilities. For us, what we saw was that while the inner loop was getting sped up by AI, the outer loop was rapidly becoming the bottleneck. Um, we were seeing tools like Cursor, Windsurf, Copilot, V0, Bolt, all of those, producing larger volumes of code than we were used to, than we had ever seen before. But we were also seeing our developers suddenly have to review higher volumes of code, test higher volumes of code, merge higher volumes of code, and deploy higher volumes of code. That's what brought us to say there has to be a new outer loop here. This, the way that things are going, this isn't going to work. We're going to break down. We're watching the problems that used to only ail large companies start to ail all companies, where we were seeing companies deal with higher and higher and higher volumes of code. The requirements for the new outer loop, then, look a lot like the problems that larger companies have always had to deal with. You need tools to better prioritize, track, and get notified about pull requests. You need driver assist features to help reviewers focus and streamline the code review process. You need optimized CI pipelines and merge queues to be able to handle the sheer volume of code changes that are now happening. And you need better deployment tools. Oops. Um, when we first started looking at this through sort of an AI-first lens, we started to see that, well, the problems are being created by AI, they can also probably be solved by AI. ### AI-Native Solution **Tomas Reimers** [3:19] We can probably start to streamline a lot of these processes which have previously had to been manual, previously were parts of the process that developers did not enjoy, did not want to do. Um, we wanted to see self-driving code review solutions where we no longer had to do those very manual and painful parts of review, but we could actually start to really focus on what matters most to the developers, making sure that your product can get out to users and that the features work as expected. Um, we were seeing that AI-generated feedback wasn't perfect. And because of that, we were starting to think that bots weren't enough. I think an early, uh, an early vision of ours was, well, can we solve this by just adding AI teammates,right? Maybe it's background agents, maybe it's reviewers, maybe it's a whole lot of teammates to the workflow. And while we think that's part of the story, we don't think that's enough. We think that, as we've built with Diamond, that your entire toolchain has to be AI-native, not just your IDE. If you really are going to embrace AI in the age of development, if you're going to accept the fact that developers are going to be orders of magnitude more productive than they ever have before, you need tooling that reflects that. We started by building Diamond, so the winning AI code review platform, with high signal, low noise, as a deep understanding of the codebase and change history. We summarize, prioritize, and review each change, and we integrate with your CI and your testing infrastructure to correct, uh, to summarize errors and correct failures. ### Diamond Platform **Tomas Reimers** [4:35] Um, our hope with it, and what we've started to see as we've rolled it out to larger and larger customers and enterprises too, is we review, we reduce code review cycles, we enforce quality and consistency, and we keep your code private and secure. Um, it's high signal, it's zero setup, it's actionable with one-click suggestions, and it's customizable. It's already being used by some of the fastest-moving companies in the world. It's expanding a lot more than we can even say publicly. Um, and I hope that you all will embrace the idea that AI can change your entire developer workflow, not just your IDE. Um, by the numbers, we see comments that our AI bot leaves to be downloaded at less than a 4% rate, and to be accepted, meaning integrated into the pull request, um, that they were left on, at a higher rate than human comments are. Human comments are integrated about somewhere between 45 and 50%. We're watching our Diamond comments be accepted about 52%. We've spent a lot of time tuning that. That's, that number is actually new as of March for us. Um, that's, that's what I have to tell you around Graphite, um, what I have to tell you around Diamond. I hope you give it a shot, and, and thanks for having me. --- This library is powered by PodHood (https://podhood.com), the podcast website platform.