Gergely Orosz · 7 min read · Gen AI Tools
DHH’s new way of writing code
Read the original on newsletter.pragmaticengineer.com →
In this episode, David Heinemeier Hansson explains how his approach to building software has shifted from writing code by hand to using AI agents and agent-first workflows. He shares practical tooling (tmux, neovim, Gemini 2.5, Opus), Rails' role in enabling agent work, and why beauty in code and design remains a guide to quality, while noting AI's uneven impact on engineers.
Key Takeaways
- AI tooling with agent harnesses has transformed coding, moving from autocomplete-style coding to powerful agents like Opus and Gemini 2.5.
- Beautiful code and products are signals of correctness; craft and aesthetics matter in both design and implementation.
- DHH's workflow uses tmux, neovim, a dual-model setup, and integrated testing within Rails to empower agents and review outputs efficiently.
- AI-enabled work unlocks tasks previously out of reach (e.g., micro-optimizations) and reshapes the software engineer role, with implications for senior vs. junior engineers.
Excerpt
Stream the latest episode Listen and watch now on YouTube , Spotify , and Apple . See the episode transcript at the top of this page, and timestamps for the episode at the bottom. Brought to You by • Statsig – ⁠ The unified platform for flags, analytics, experiments, and more. Stop switching between different tools, and have them all in one place. • WorkOS – Everything you need to make your app enterprise ready. WorkOS gives you APIs to ship enterprise features in days. Check out WorkOS.com • Sonar – The makers of SonarQube, the industry standard for automated…