AI-generated code doesn’t have to be throwaway code. Here’s how we used Claude Code to build a fully-tested, production-quality Rails prototype in two weeks, complete with a robust test suite, clean commits, and code we were proud to have written.
Chad and Will examine the ever expanding AI bubble and ponder on what we can expect it to see evolve in the coming years.
Celebrate Giant Robots’ 600th episode in style as Sami pulls together thoughtbot staff old and new to celebrate this monumental milestone.
In addition to our regular tech leader event in London, we’re partnering with local tech leaders to bring the event to Manchester, Bristol, Brighton, and Edinburgh this year.
Chad and Will start the new year off right by discussing their aspirations for 2026.
What’s one of the biggest challenges with using AI for QA? It’s the lack of programmability. We set out to find a solution by pairing Playwright MCP with several different LLM models. Find out where we landed.
We’ve been running product design sprints for over a decade. Now Claude and Claude Code are helping us prototype faster than ever—without sacrificing quality. Here’s how we built a working prototype in hours, not days.
Doing manual QA can be slow and tedious, but can ChatGPT agent handle real product QA? We ran a few experiments checking FrontrowMD widgets across sample web pages and discovered a lot of potential—plus a few pitfalls.
Chad talks with developer and guitarist Nick Merwin about the challenges of balancing his career in development with his life as a musician.
Trying to optimize your AI coding workflow? One size doesn’t fit all. During an AI pair programming session, we discovered some insights about control, context and trust that might help you sharpen your own process.