✍️ New Blog Post: Building a codebase that compounds with each new AI agent
Every month a shiny new agent framework drops. I used to chase them. It didn’t make me faster.
What did help was hardening my codebase. If you spend ~20% getting the basics right, every new model/agent feels like a free upgrade instead of a week of churn. Here’s the short list I’d set up on any fresh project:
1. Strict types / hints — Turn on strict modes (TypeScript, Python, Go, Rust). Clear contracts = better suggestions and safer edits.
2. Schema validation at boundaries — Validate all external I/O (Zod, Pydantic, Serde). Fail fast so the model fixes to the contract instead of guessing. Silent shape-drift is where weekends go to die.
3. Linters and formatters in CI — ESLint/Prettier/Ruff catch drift early. One style, smaller diffs, less “why did this file change?” noise for you and the model.
4. Docs as context — Short docstrings and inline notes turn into high-signal prompts. I ask questions first, code later (see: “Ask First, Code Later”).
5. Well-known frameworks — Rails, Django, Next.js come with years of patterns. The AI has seen those patterns. You’ll both argue less about basics.
.. and lots more! read about it in my blog post below ⬇️
https://pirosb3.io/posts/best-tools-for-being-a-great-ai-engineer 3 replies
3 recasts
18 reactions
1 reply
0 recast
0 reaction
1 reply
0 recast
1 reaction