My current favorite readings on coding with AI

Update 2026-05-11: Added Daniel Euchar’s blog, Matt Pocock’s skills and Vlad Khononov’s modularity plugin. Add reference to Mario Zechner. Downplaying the Compound Engineering plugin.

Update 2026-04-11: Added Ivett Ördög’s video, and sections on specific topics: TDD and testing, harnesses and guardrails, spec-driven development, and reviewing AI output.

I’ve been experimenting with coding with AI intensely for the past 13 months. Along the way, some things I read stayed with me and I would recommend them to anyone on this learning journey. These are some of my favorites; I’m only including choice representatives from each category, to keep this post short.

Personal workflows

It’s always fascinating to read about talented individuals’ personal work habits. Here are a few favorites out of many.

Team and company workflows

Pattern languages

Emily Bache recently argued that, given that traditional TDD katas are no match for AI coding assistants, we should study patterns instead. She has a very good point, though I think that finding existing open source codebases and making them safe to operate with AI is also a very good exercise.

Here are the only two coding-with-AI pattern collections I know

Book

Not many books on this subject; of the ones I read, this one is the only one I like:

Theories

Specific topics

DDD

Some skills I saw about DDD, focus on the technicalities of Value Objects and Entities. Surely these are important, but even more fundamental is paying attention to the domain language. DDD is about communication, and working with AI is also about communication. Building a precise vocabulary helps, because it makes our conversations, and our code, more concise and precise.

Matt Pocock’s Skills plugin contains the weirdly named “grill-me-with-docs” skill, that can be used to build a vocabulary from scratch, or to revise a task description against an existing one.

TDD and testing in general

Architectural design

Architectural design is essential, in general, and it becomes even more important when working with AI, because AI does not care about the maintainability of our code, unless we direct it specifically to do something about it. Now, modularity is often praised, but is rarely explained well. It’s not enough to say “improve my code”: we should explain clearly what we consider “better”.

Harnesses and guardrails

Spec Driven Development

Reviewing AI output

Finally…

Ivett’s recommendation is gold: Never use a prompt from anyone else, unless you have reviewed that prompt

Want to leave a comment? Please do so on LinkedIn!

#AI