# Ask HN: How would you learn AI-assisted development from the ground up? > Source: > Published: 2026-07-29 15:31:35+00:00 I'm a director/exec, not a software engineer. Background's mostly data analytics, SQL and Excel day to day, some R and PostgreSQL. Years ago I could hack together basic HTML/CSS/PHP too. Got into AI early and now use ChatGPT and Claude constantly. With their help I've built a handful of web apps, some Python scripts and desktop tools, and an Android app on Supabase with real multiple users. So I can build things. But I'm very aware there are big holes underneath it. I can usually get something working without really knowing why it works, whether it's actually well built, or what's going to break down the road once it gets more complex. Feels like it's time to go back to fundamentals. Michael Jordan still worked on his footwork, that kind of thing. What I'm hoping to get to eventually: * build small useful apps, windows/mac/android/ios/web * automate chunks of my own and my team's work * maybe build a simple SaaS at some point * generally not get left behind, open to this reshaping my career or spinning into a side thing Was hoping for something structured, starting from prompt/context engineering and working into real programming fundamentals, APIs, databases, architecture, security, testing, deployment. Problem is anything I find is stale within months given how fast this moves. Not looking for free necessarily, and definitely not looking for "learn to code in a weekend." Willing to put in real time. For people who've gone down this road already: what's actually worth learning properly, what's fine to just learn enough to supervise, and what can honestly just stay AI's job? P.S.: Yes I polished/refined this post using AI, but I first wrote it all myself (the original was twice as long). Comments URL: [https://news.ycombinator.com/item?id=49098829](https://news.ycombinator.com/item?id=49098829) Points: 2 # Comments: 0