12 Comments
User's avatar
Dean Taplin's avatar

Thanks for such a detailed article with a lot of practical advice. I like the planning spec approach and need to explore that more in 2026. I too have had success with AI reviewing AI for a second opinion.

Expand full comment
Leong Shi Wei's avatar

Extremely valuable advice sirr!! This covers basically everything in my fragmented notes about AI assisted dev. Js one thing though, do u maintain a change log or smt? Is that necessary?

Expand full comment
Franjosie's avatar

I wholeheartedly endorse this approach. I’m gaining a wealth of knowledge by utilizing AI in this way. As a systems engineer, I typically don’t implement much, but I do specify functionality at a more abstract requirement level for my team. Now, I can iterate on my ideas much faster before discussing them in more detail with the developers.

Expand full comment
Bored Girl Builds's avatar

Thank you for sharing!

Expand full comment
Addy Osmani's avatar

My pleasure!

Expand full comment
Guney Topcu's avatar

Love it!

Expand full comment
Bek Tesfatsion's avatar

A key takeaway: Developers should use only familiar tech stacks, as human review of AI-generated code requires understanding the implementation. It goes without saying that this step would be like a bottleneck to the process and could end up slowing progress. What do you guys think?

Expand full comment
Janusz Hain's avatar

Great post, I think the most interesting so far. Any chance to share some examples of plan templates or any docs that you feed AI to AI? Or do you use default ones in Cursor / Antigravity? For me the default ones are okayish for small tasks, but I still prefer to build my specifications that go much deeper than default ones

Expand full comment
Sushobhit Rajan's avatar

Thanks for sharing

Expand full comment
Tolis Christomanos's avatar

TLDR don’t be lazy with AI

Expand full comment
Andre Pratama's avatar

Love your sharing 🙌🏻

Expand full comment
Hoang Nguyen's avatar

Thanks Addy, for sharing this detailed workflow, it's incredibly thoughtful and aligns closely with how I approach how AI augment engineer workflow. I especially appreciate the emphasis on upfront specs, iterative chunks, extensive context, and always keeping a human in the loop with careful review and testing. These principles have been core to my own process too.

On that note, I've been building something similar: AI-DevKit, a CLI toolkit for structured AI-assisted development with phase-based templates (requirements, design, planning, etc.) and setups for tools like Cursor, Claude Code, etc. It's all about enforcing disciplined workflows while keeping the engineer in control.

Would love to hear your feedback if you get a chance to check it out: https://github.com/codeaholicguy/ai-devkit (or https://ai-devkit.com/).

Thanks again for the great post!

Expand full comment