Gergely Orosz · 7 min read · Gen AI Tools
Building OpenCode with Dax Raad
Read the original on newsletter.pragmaticengineer.com →
In this Pragmatic Engineer Podcast episode, Dax Raad, co-founder of OpenCode, discusses the gaps in developer tooling that led to OpenCode, the benefits of open source, and how AI is shaping software development. The conversation covers OpenCode’s growth strategy, partnerships after Claude Code’s blocking, GPU bottlenecks, and why AI coding tools don’t automatically speed up engineering teams, with the author sharing 14 takeaways.
Key Takeaways
- AI makes coding easier, but the hard problems don’t vanish; you still need to think through challenges.
- Thinking upfront about direction beats rushing to prototype, especially before product-market fit is found.
- Shipping 10x more features can lead to a Frankenstein-like product and higher maintenance burden.
- No AI-native coding agent wins solely on AI; competition remains even with advanced AI tooling.
- For OpenCode, product positioning—especially its open-source stance—drives growth beyond just speed of execution.
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 • Antithesis – if you’re using agentic workflows, you need to be extremely clear about what you’re building and how your system should behave. Antithesis brings specification and verification together, making your agents faster, smarter, and safer. And when you’re using Antithesis, you’ll have greater clarity about your code as well. Learn more . • WorkOS – The fastest AI-native teams have…