DIY dev tools: How this engineer created “Flowy” to visualize his plans and accelerate coding

By How I AI Podcast

Categories: AI, Product

Summary

CJ Hess shares how he uses Claude Code to build custom AI engineering tools and workflows, including a planning system called "Flowy" that visualizes code structure. He emphasizes the importance of personalizing your developer environment with AI-assisted tools to solve previously intractable problems like environment setup and configuration.

Key Takeaways

  1. Build a personal ecosystem of custom tools around Claude Code using skills to continuously improve your workflow efficiency as an individual engineer.
  2. Use Claude Code to automate previously unsolvable developer chores like linter configuration mismatches and environment setup that previously required manual workarounds.
  3. Implement markdown-based planning files with visual flowcharts to iterate on code architecture before implementation, increasing confidence in code generation.
  4. Claude Code's superior intent understanding from steerable prompts allows it to pick up on engineer intuition better than other models, making it worth optimizing your workflow around.
  5. Onboard new team members by having them ask Claude Code to understand the repository and set up their entire development environment end-to-end.

Topics

Transcript Excerpt

Working with Claude is just such a delight. It just feels so steerable and I think the one thing it really has is intent understanding. When I wanted to dig deep, it just does it and it's really enabled me to build a little ecosystem of my own tools around it. >> I think environment setup and developer setup is such an underappreciated use case. One of the things that I know you really care about is effective planning and you've come up with a way that you do your planning that I think is pretty...