Viewing profile — hoangnnguyen

This might interest you, you can integrate with it to get the status of not only Claude but other harnesses such as Codex, Pi, Opencode, Copilot, etc https://ai-devkit.com/docs/8-a…

Hi, I’m the creator of AI DevKit. Problem that you are facing is one of the thing made me build this. Once you have 4–5 active agent sessions, the bottleneck becomes remembering wh…

Thanks for sharing, I am also into this problem currently, exploring how can let the agents communicate with each other effectively. I really love your metaphor. I went the other w…

[flagged]

What are your favorite hooks tips and tricks?

[flagged]

Appreciate it, I know there are so much room to improve, looking forward to hearing feedback from you.

Thank you, appreciate it

In my requirement review and design review phase, I specific that the agent need to review edge cases and come up with 3 suggestions. So that I can choose. In case it is not match …

I wrote the full breakdown here: https://codeaholicguy.com/2026/04/11/how-my-ai-workflow-evol...

Over the last 6 months, I have been evolving my AI coding workflow while building AI DevKit. The shift that mattered most was not better code generation. It was moving from reusabl…

I appreciate you taking the time to write this. There are a few fair points here. I agree that AI is not automatically better at planning than an experienced engineer. In fact, I w…

I share more about my experience with Agentic Engineering and how I design workflows to make that leverage compound over time in the full article below. Link: https://codeaholicguy…

If you are still coding the same way you did two years ago, you might be falling behind without realizing it. Not because you are not capable. Not because you are not using AI. But…

I also wrote a detailed breakdown of: - How tokens and context windows actually affect stability - Why coding degrades faster - A practical context stack model - Why on-demand CLI …