I've had the same type of experience where I feel like the knowledge barrier for a lot of projects has been made much smaller than it used to be :D
btw, I have a couple of questions just out of curiosity: What tools do you use besides Claude? Do you have a local or preferred setup? and do you know of any communities where discussion about LLM/general AI tool use is the focus, amongst programmers/ML engineers? Been trying to be more informed as to what tools are out there and more up to date on this field that is progressing very quickly.
Claude is my favorite and at work it's what we officially use. At home I pay for claude by the token but I have a gemini and chatgpt account. So at home I use a lot more gemini cli and codex.
For my setup, I make sure I have good markdown files and I use beads. I'll usually have an AGENTS.md, CLAUDE.md, GEMINI.md in every project and 99.9% of the time they're the exact same. I always make sure to keep these files up to date. If the LLM does something I don't like and I can foresee it being a problem, I'll add it to the markdown file as something not to do.
My markdown files generally have multiple sections. There's always a good chunk describing the app (or in a non software case, the goal or purpose). Some design/architecture decisions will make it into the markdown files. How to build/test are in the markdown files.
I think it helps that I already have good patterns and structure to most things I build. I have moved more to a monorepo since LLMs came out. So an android app won't be in a separate repo as the webapp, instead they're all in the same repo with different directories (frontend vs {app}-android/{app}-iphone/{app}-mobile). Everything I build gets deployed to AWS and I have good patterns for that. Make for builds/deploys/tests, I don't ever run terraform or npm or maven or any other builds on the cli, if I'm running it it goes in the Makefile. All apps follow the same Makefile patterns where certain commands all get rolled up into the same one (make plan, make build, make deploy) using the same general env vars.
Now for tools and such, I feel like just the cli agents themselves are it. On personal stuff that's 100% all I use, the cli agent. At work I integrate with some MCPs and I've created and use some skills/plugins, but tbh I don't feel like they make a big difference or are necessary. I think the non-deterministic nature of the tool makes these unnecessary. Like sometimes I have to explicitly tell the agent to use the MCP. Sometimes the MCP takes up more context than having the llm create a script to hit and API and recreate the MCP's functionality.
And when I have questions, like you did here, I ask the llms first. I ask a lot of "meta" questions to the llm in my sessions even. I like to think it primes it for going down the path you want.
The sad thing is once I learned what an em-dash was in college, I started using it everywhere. Fast forward a few decades and suddenly... Oh wait... You don't suppose I'm a... No. I couldn't be. I didn't use a dash in this entire reply!
I want to find a good use for clojurescript.
It would be cool to build a personal site with an OS theme.
Additionally with enough extensibility it could become like emacs.
https://en.wikipedia.org/wiki/Trypophobia maybe? Could lean into that as an esthetic - everything is always misaligned carefully by 1 pixel, using trypophobia fonts which overload ligatures to punch tiny holes into each letter...
btw, I have a couple of questions just out of curiosity: What tools do you use besides Claude? Do you have a local or preferred setup? and do you know of any communities where discussion about LLM/general AI tool use is the focus, amongst programmers/ML engineers? Been trying to be more informed as to what tools are out there and more up to date on this field that is progressing very quickly.
reply