The State of Code Quality with Saša Jurić
Elixir Wizards
When a PR is unreviewable
Saša recommends telling authors when a PR is too big, pairing to split work, and favoring incremental greenfield changes.
In this episode of Elixir Wizards, hosts Charles Suggs and Emma Whamond sit down with Saša Jurić, Elixir mentor and author of Elixir in Action, to discuss software craftsmanship in the age of AI. As AI coding tools become increasingly capable, Saša argues that the real challenge isn't generating code, it's maintaining quality, clarity, and shared understanding within a codebase.
We explore the difference between correct code and good code, and why code is more than a set of instructions for a machine to execute. Code is also documentation, communication, and a long-term investment that future developers must be able to understand and maintain. Saša shares his concerns about the growing "theater of pull requests," where teams go through the motions of code review without creating meaningful opportunities for learning, feedback, or knowledge sharing.
The hosts and Saša talk about practical ways to work effectively with AI, including taking smaller steps, carefully reviewing AI-generated code, and using AI as a collaborative tool rather than an autonomous developer. Throughout the discussion, Saša challenges the industry's obsession with speed and makes the case that the principles of good software development (incremental progress, clear communication, and human judgment) remain important in the age of AI.
Key Topics Discussed
- The difference between correct code and good code
- Code as communication, documentation, and shared understanding
- The "theater of pull requests" and ineffective review practices
- How AI is changing software development workflows
- Using AI as a collaborator rather than a replacement
- Why smaller, incremental changes lead to better outcomes
- Human oversight in AI-assisted development
- Balancing development speed with maintainability
- Pull request size and review effectiveness
- Commit history as a tool for storytelling and context
- The risks of accumulating technical debt faster with AI
- Testing and validating AI-generated code
- Refactoring AI-generated solutions for clarity
- Applying agile principles to AI-assisted workflows
- The role of experience and judgment in software design
- Why software craftsmanship still matters in the age of AI
Links mentioned
Code Complete by Steve McConnell https://khmerbamboo.wordpress.com/wp-content/uploads/2014/09/code-complete-2nd-edition-v413hav.pdf
Harness AI for DevOps, Testing, and AppSec https://www.harness.io/
Claude Code https://claude.com/product/claude-code
Claude Code GitHub https://github.com/anthropics/claude-code
Pull Request for Oban https://github.com/oban-bg/oban/pull/331
SMPP https://en.wikipedia.org/wiki/Short_Message_Peer-to-Peer
OpenAI Codex https://chatgpt.com/codex/
Opus AI https://opus.ai/
Tidewave https://tidewave.ai/
Credo Static Code Analysis https://github.com/rrrene/credo
https://smartlogic.io/podcast/elixir-wizards/s11-e09-static-code-analyzer-elixir-credo-ruby-rubocop/
Link to Sasa’s X post https://x.com/sasajuric/status/2029522378196238503
Saša Jurić “Tell Me A Story” at Goatmire https://www.youtube.com/watch?v=GOrKfCs-mr0
https://meks.quest/blogs/the-theatre-of-pull-requests-and-code-review
Looks Good to Me: Constructive Code Reviews by Adrienne Braganza https://www.manning.com/books/looks-good-to-me
Towards Maintainable Elixir: Testing https://medium.com/very-big-things/towards-maintainable-elixir-testing-b32ac0604b99
TDD, Where Did It All Go Wrong (Ian Cooper) https://youtu.be/EZ05e7EMOLM
Special Guest: Saša Jurić.
The AI-powered Podcast Player
