- Figuring out the architecture of a project you just came into
- Tracing the root cause of a bug
- Quickly implementing a solution with known architecture
I figured out that above all, what makes or breaks success is context engineering. Keeping your project and session documentation in order, documenting every learning you've made along the way (with the help of AI), asking AI to compose a plan before implementing it, iterating on a plan before it looks good to you. Sometimes I spend several hours on a plan markdown document, iterating on it with AI, before pressing "Build" button and the AI doing it in 10 minutes.
Another important thing is verification harness. Tell the agent how to compile the code, run the tests - that way it's less likely to go off the rails.
Overall, since couple of month ago, I feel like I got rid of the part of programming that I liked the least - swimming in technicalities irrelevant for the overall project's objectives - while keeping what I liked the most - making the actual architectural and business decisions.
I wrote a blog recently about the approach that works for me: https://anatoliikmt.me/posts/2026-03-02-ai-dev-flow/
And this is a tool for context engineering I made specifically to support such a flow: https://ctxlayer.dev/