To me, this kind of stuff is like bloated boilerplates such as "full-stack e-commerce SaaS NextJS boilerplate." I never use them because I want more control and fewer unpredictabilities. They seem to save you some time, but you will pay a lot more for it later when you encounter deep bugs or need to refactor. For this reason, I won't use prompt templates for agentic coding tools either. There have been enough suggestions to write your own AGENTS.md and not overcomplicate the prompts.
Superpowers: How I'm using coding agents in October 2025
241–242 of 242 posts
Re: Superpowers: How I'm using coding agents in October 2025
#242I'm so curious around what people's median experience is of AI coding tools. I've tried agents every now and then, recently for something very simple- add an option to request csb format in a data api. The results were, well, not good. . . I ended up undoing literally all changes because writing from scratch was a lot easier than trying to refactor the total mess it has made from what I'd have thought was a trivial f…
As someone who has been fairly negative towards AI until recently, the problem is how you use it. If you just tell it some vague feature to make, it's gonna do whatever it's gonna do and maybe it will be good, maybe it won't. It probably won't. The more specific you are the better it will do. Instead of trying to 100x or 1000x your effort, try to just 2x or 3x it. Give it small specific tasks and check the work thoro…
That sounds fine, but I wouldn't expect you'd still be at 2× to 3× then. Maybe closer to 1.2× to 1.3× (although studies seem to show it's more often actually 0.9×). Coding is already barely 10% of the work, the agents won't help much with the other parts, and now you have a whole load of additional things to check and potentially fix, which you didn't have to before because they're obvious to a human mind.