How I write software with LLMs
stavros.io
How I write software with LLMs
1–10 of 544 posts
Re: How I write software with LLMs
#2I like reading these types of breakdowns. Really gives you ideas and insight into how others are approaching development with agents. I'm surprised the author hasn't broken down the developer agent persona into smaller subagents. There is a lot of context used when your agent needs to write in a larger breadth of code areas (i.e. database queries, tests, business logic, infrastructure, the general code skeleton). I've also read[1] that having a researcher and then a planner helps with context management in the pre-dev stage as well. I like his use of multiple reviewers, and am similarly surprised that they aren't refined into specialized roles.
I'll admit to being a "one prompt to rule them all" developer, and will not let a chat go longer than the first input I give. If mistakes are made, I fix the system prompt or the input prompt and try again. And I make sure the work is broken down as much as possible. That means taking the time to do some discovery before I hit send.
Is anyone else using many smaller specific agents? What types of patterns are you employing? TIA
1. https://github.com/humanlayer/advanced-context-engineering-f...
Re: How I write software with LLMs
#3This was on the front page and then got completely buried for some reason. Super weird.
Re: How I write software with LLMs
#4I like reading these types of breakdowns. Really gives you ideas and insight into how others are approaching development with agents. I'm surprised the author hasn't broken down the developer agent persona into smaller subagents. There is a lot of context used when your agent needs to write in a larger breadth of code areas (i.e. database queries, tests, business logic, infrastructure, the general code skeleton). I'v…
that reference you give is pretty dated now, based on a talk from August which is the Beforetimes of the newer models that have given such a step change in productivity.
The key change I've found is really around orchestration - as TFA says, you don't run the prompt yourself. The orchestrator runs the whole thing. It gets you to talk to the architect/planner, then the output of that plan is sent to another agent, automatically. In his case he's using an architect, a developer, and some reviewers. I've been using a Superpowers-based [0] orchestration system, which runs a brainstorm, then a design plan, then an implementation plan, then some devs, then some reviewers, and loops back to the implementation plan to check progress and correctness.
It's actually fun. I've been coding for 40+ years now, and I'm enjoying this :)
Re: How I write software with LLMs
#5This was on the front page and then got completely buried for some reason. Super weird.
On the front page at the moment. Position 12
Re: How I write software with LLMs
#6This was on the front page and then got completely buried for some reason. Super weird.
[flagged]
Re: How I write software with LLMs
#7I like reading these types of breakdowns. Really gives you ideas and insight into how others are approaching development with agents. I'm surprised the author hasn't broken down the developer agent persona into smaller subagents. There is a lot of context used when your agent needs to write in a larger breadth of code areas (i.e. database queries, tests, business logic, infrastructure, the general code skeleton). I'v…
that reference you give is pretty dated now, based on a talk from August which is the Beforetimes of the newer models that have given such a step change in productivity. The key change I've found is really around orchestration - as TFA says, you don't run the prompt yourself. The orchestrator runs the whole thing. It gets you to talk to the architect/planner, then the output of that plan is sent to another agent, aut…
Can you bolt superpowers onto an existing project so that it uses the approach going forward (I'm using Opencode), or would that get too messy?
Re: How I write software with LLMs
#8This was on the front page and then got completely buried for some reason. Super weird.
On the front page at the moment. Position 12
Maybe I missed it. Sometimes when you're scanning for something your brain intentionally doesn't want to see it, I've noticed. Anyway I'm not Stavros obviously, just thought this was a good article.
Re: How I write software with LLMs
#9I wanted to know how to make softwares with LLM "without losing the benefit of knowing how the entire system works" and "intimately familiar with each project’s architecture and inner workings", while "have never even read most of their code". (Because obviously, you can't.) But OP didn't explain that.
You tell LLM to create something, and then use another LLM to review it. It might make the result safer, but it doesn't mean that YOU understand the architecture. No one does.
Re: How I write software with LLMs
#10I'm not sure the notion I keep seeing of "it's ok, we still architect, it just writes the code"(paraphrased) sits well with me.
I've not tested it with architecting a full system, but assuming it isn't good at it today... it's only a matter of time. Then what is our use?