Generative AI coding tools and agents do not work for me

To some degree, traditional coding and AI coding are not the same thing, so it's not surprising that some people are better at one than the other. The author is basically saying that he's much better at coding than AI coding.

But it's important to realize that AI coding is itself a skill that you can develop. It's not just , pick the best tool and let it go. Managing prompts and managing context has a much higher skill ceiling than many people realize. You might prefer manual coding, but you might just be bad at AI coding and you might prefer it if you improved at it.

With that said, I'm still very skeptical of letting the AI drive the majority of the software work, despite meeting people who swear it works. I personally am currently preferring "let the AI do most of the grunt work but get good at managing it and shepherding the high level software design".

It's a tiny bit like drawing vs photography and if you look through that lens it's obvious that many drawers might not like photography.

> But it's important to realize that AI coding is itself a skill that you can develop. It's not just , pick the best tool and let it go. Managing prompts and managing context has a much higher skill ceiling than many people realize

No, it's not. It's something you can pick in a few minutes (or an hour if you're using more advanced tooling, mostly spending it setting things up). But it's not like GDB or using UNIX as a IDE where you need a whole book to just get started.

> It's a tiny bit like drawing vs photography and if you look through that lens it's obvious that many drawers might not like photography.

While they share a lot of principles (around composition, poses,...), they are different activities with different output. No one conflates the two. You don't draw and think you're going to capture a moment in time. The intent is to share an observation with the world.

> It's something you can pick in a few minutes

You can start in a few minutes, sure. (Also you can start using gdb in minutes) But GP is talking about the ceiling. Do you know which models work better for what kind of task? Do you know what format is better for extra files? Do you know when it's beneficial to restart / compress context? Are you using single prompts or multi stage planning trees? How are you managing project-specific expectations? What type of testing gives better results in guiding the model? What kind of issues are more common for which languages?

Correct prompting these days what makes a difference in tasks like SWE-verified.

I feel like there is also a very high ceiling to how much scaffolding you can produce for the agents to get them to work better. This includes custom prompts, custom CLAUDE.md files, other documentation files for Claude to read, and especially how well and quickly your linting and tests can run, and how much functionality they cover. That's not to mention MCP and getting Claude to talk to your database or open your website using Playwright, which I have not even tried yet.

For example, I have a custom planning prompt that I will give a paragraph or two of information to, and then it will produce a specification document from that by searching the web and reading the code and documentation. And then I will review that specification document before passing it back to Claude Code to implement the change.

This works because it is a lot easier to review a specification document than it is to review the final code changes. So, if I understand it and guide it towards how I would want the feature to be implemented at the specification stage, that sets me up to have a much easier time reviewing the final result as well. Because it will more closely match my own mental model of the codebase and how things should be implemented.

And it feels like that is barely scratching the surface of setting up the coding environment for Claude Code to work in.