HN user

mgaudin

46 karma
Posts18
Comments7
View on HN

Author here. This is the first part of a series based on our experiences at MadKudu, where we've shifted to treating AI agents as full-time developers, not just assistants.

We found that traditional development practices break down completely under this model. I've distilled our learnings into 11 principles that have made AI-native development practical and significantly boosted our team's productivity (e.g., by focusing on mono-repos, strict typing, and redefining the engineer's role towards documentation and architecture).

Happy to discuss these principles and answer any questions.

I understand, and I've tried this for a long time, but unfortunately it didn't work very well for me.

First, the level of uncertainty is very high right now, and I can't afford to have a fixed calendar for the whole week. In fact, it's pretty rare that I manage to stick to the same schedule for even half a day. :X Also, it's often extremely difficult to estimate how long certain tasks will take because they involve both spending time with people (who, by definition, are highly unpredictable) and thinking strategically (which can take anywhere from 2 minutes to 2 hours).

That said, I do relate to the idea that "less freedom" can lead to "more happiness"! I try to apply this as much as possible when it makes sense, especially in my personal life.

You are absolutely right—I should keep some slots for higher-level items, like the week's objectives or even longer-term goals. This is something I'm actually struggling with right now, so thanks for the tip!

As for the Ivy Lee method, I'm not familiar with it, but I'll definitely check it out!