The most important investment in agentic coding velocity may have nothing to do with agents. Amplitude tripled its PR volume in six months. PR cycle time went from 5.2 hours to 44 minutes. Almost all of that came from fixing unglamorous infrastructure. 𝐂𝐈 𝐟𝐫𝐨𝐦 𝟑𝟎 𝐦𝐢𝐧𝐮𝐭𝐞𝐬 𝐭𝐨 𝟑: they swapped the JavaScript toolchain for native equivalents (tsc to tsgo, ESLint to oxlint, Prettier to oxfmt), moved to affected-only builds in Turborepo, and ran independent stages concurrently. Most tools got about 10x faster. 𝐅𝐮𝐥𝐥 𝐬𝐭𝐚𝐜𝐤 𝐮𝐩 𝐢𝐧 𝟐𝟖 𝐬𝐞𝐜𝐨𝐧𝐝𝐬: a custom CLI built on devbox starts every local service with one command, down from 3 minutes. 𝐕𝐚𝐥𝐢𝐝𝐚𝐭𝐢𝐨𝐧 𝐰𝐢𝐭𝐡 𝐧𝐨 𝐥𝐨𝐜𝐚𝐥 𝐬𝐞𝐭𝐮𝐩: add a label to a PR and get a frontend preview in under five minutes, or an ephemeral copy of the backend stack in the cloud. Once you have a full app stood up in 30 sec on every PR, testing and verification become much faster which decreases time to merge. 𝐑𝐞𝐯𝐢𝐞𝐰 𝐬𝐜𝐨𝐫𝐞𝐝 𝐛𝐲 𝐫𝐢𝐬𝐤: a model rates each code change on size, scope, test coverage, and API surface, and low-risk changes merge with no human. Cursor's Bugbot reviews every PR, and bug reports fell 55% even as PR volume tripled. Once CI dropped under five minutes, engineers stopped working locally. Remote is the new dev environment.

I’m excited to finally announce the newest edition my Stanford course 𝗧𝗵𝗲 𝗠𝗼𝗱𝗲𝗿𝗻 𝗦𝗼𝗳𝘁𝘄𝗮𝗿𝗲 𝗗𝗲𝘃𝗲𝗹𝗼𝗽𝗲𝗿. It has been 9 months in the making. Last November, with the release of Claude Opus 4.5, coding agents experienced a step function improvement in capability. We all felt it. The LLMs were more powerful, could reason for longer, solve harder tasks. This year’s iteration of my course reflects the 2026 metamorphosis of software engineering. My core belief is simple: AI-native developers of the LLM era are going to become the most important members of any software organization. I have designed my course to train this next generation of engineers. 𝗪𝗵𝗮𝘁’𝘀 𝗱𝗶𝗳𝗳𝗲𝗿𝗲𝗻𝘁 𝘁𝗵𝗶𝘀 𝘁𝗶𝗺𝗲 𝗮𝗿𝗼𝘂𝗻𝗱 First, 85% of my Fall 2025 class material is being thrown out. The Fall 2026 syllabus reflects the core capabilities AI-native engineers must have: agent skills, advanced context engineering, MCP portals, agent-ready codebase principles, agentic code review, security, parallelizing background agents, software factories, and more. Second, I am going to teach my students how to have software taste. Every student will be required to ship pull requests to production-grade, real-world codebases. The course is collaborating with the top open-source AI repos who will offer support and mentorship to students on how to meaningfully contribute to their projects. This has never been done before in any university course so I am incredibly grateful to our OSS Partners: @browserbase, @HeyGen, @CopilotKit, @semgrep, @OpenHandsDev, @milvusio, @marimo_io, Pi, @crewAIInc, @warpdotdev, @vercel, @cmux, @arizeai, @UnslothAI, and @anyscalecompute. 𝗪𝗵𝗮𝘁’𝘀 𝘀𝘁𝗮𝘆𝗶𝗻𝗴 𝘁𝗵𝗲 𝘀𝗮𝗺𝗲 I’m fortunate to again have AI software engineering leaders and founders as guest speakers to share their learnings from building top coding agent products. Thank you to @leerob from @cursor_ai, @bcherny of @claudeai code, @EnoReyes of @FactoryAI, @silasalberti of @cognition, @0xine of @semgrep, Rajesh Bhatia of @Cloudflare , @amasad of @Replit, and @eladgil. All resources will be available online. All classes will be available to the public. 9/22 on Stanford campus. See you in class. 

When you're the one responsible for the output, make sure to maintain the reins on your coding agents. A wise warning from @badlogicgames, creator of Pi, on the risks of dark factories. This was one of my favorite conversations packed with insights. Check it out:

Announcing a new episode of 𝗧𝗵𝗲 𝗕𝘂𝗶𝗹𝗱 𝗦𝘆𝘀𝘁𝗲𝗺 with @TomasReimers, co-founder and CPO of @graphite, one of the leading AI code review platforms, recently acquired by @cursor_ai. This was a practical deep dive on how top engineers are actually building with coding agents today. Some of the biggest takeaways from our conversation: - The real bottleneck in AI software engineering is rapidly becoming product thinking, not coding. - “Toy apps” and production systems require completely different trust models for agents. - Fast feedback loops, previews, smoke tests, and GUI validation matter more than ever. - Background agents are changing how engineers parallelize work. - The best builders are combining local agents + cloud agents together, not treating them as substitutes. In this build, Tomas also walks through creating a real internal Electron app from scratch using coding agents: a tool for generating Git repos in weird states like merge conflicts, rebases, detached HEADs, staged files, and more so teams can test Git-aware product flows inside Cursor. Tomas is one of the most knowledgeable people on AI code review in the world. A lot of gold in this one. Hope you enjoy it. Video in links.