Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Ask HN: What is your (AI) dev tech stack / workflow?

news.ycombinator.com

Post reply on HN
Print view View original

111–120 of 187 posts

Re: Ask HN: What is your (AI) dev tech stack / workflow?

#113

Post by dv35z »

Thanks for the great discussion. I went through all the comments, and identified common tools (counting the references in the comments). If you are interested in seeing the summary of this thread, check it out here:

https://codeberg.org/jro/Knowledge/src/branch/main/2026-06-0...

Contributions & improvements are invited and welcome - thank you!

Re: Ask HN: What is your (AI) dev tech stack / workflow?

#114

Post by browningstreet »

I’m a solopreneur working on a fairly large number of independent projects.

I use Claude Code to initiate a project using Sahil’s ME skill pack and write a high-level spec to a Linear ticket. If/when I’m ready to work on that idea, I convert it to a project, decompose the top ticket into more issues. I also have Claude code add to each issue with deepseek, sonnet or opus tags based on which is most appropriate for the issue.

Then I fire up opencode and go through each ticket. Plan, then build. Every N issues I switch to opus and have it review the work done.

Enhancements and bug reports get filed in the project. Repeat as necessary. I work pretty sequentially. I’m quite happy with the operational success of my projects. They’re all being used.

I’ve expanded this process a few times but this baseline is where things shrink to. Sometimes I use open chamber but opencode cli works for me.

Re: Ask HN: What is your (AI) dev tech stack / workflow?

#118

Post by chrismorgan »

dv35z wrote: post #107
chrismorgan wrote: post #9

I feel it’s important that this should be mentioned at least once in a thread like this: none. I choose to program the old-fashioned way, and do not anticipate this changing in the foreseeable future, and believe that I’ll cope just fine in my niche; and if it becomes commercially unviable, well, I may no longer be interested in the field anyway. I won’t go into any details on why here, because that would make it too…

Would you be open to share your "why's"? I would appreciate hearing diverse perspectives on this, and it sounds like you have experience and learnings which would be beneficial for us (at least me) to hear out. Thank you.

The thread has gone from the front page now, so I’ll share my summary of my personal reasons: https://chrismorgan.info/ai. As regards learning, I haven’t written anything down, and doing it justice would take longer than I am willing to spend now. It’s not exactly the same area, but https://www.youtube.com/watch?v=Fd-_VDYit3U> is five minutes of expert testimony to the U.S. Senate Commerce, Science, and Transportation Committee on 2026-01-15 about the resoundingly negative consequences of tech in education. There’s plenty of other well-established research in adjacent areas, things like just how valuable handwriting is for memory retention. It has been established for a long time that struggle is intrinsically valuable for human accomplishment, in areas physical and mental. It’s barely even an extrapolation to say that relying on LLMs will hinder your deep learning (irony indeed). I have no doubt that some will be able to learn better or faster with them, if they use them in disciplined fashion, but even that will be difficult, for they are designed to be addictive, just as social media is. You’ll get going a lot more quickly, but the struggle is not the only thing you’ll lose.

Humanly speaking, it truly is alarming what we’re doing to ourselves.

Re: Ask HN: What is your (AI) dev tech stack / workflow?

#119

Post by altuzar »

era86 wrote: post #40
delduca wrote: post #35

MacOS, Ghostty, Tmux, Neovim, Workmux[1], OpenCode/Claude Code, and lots of markdowns. 1 - https://github.com/raine/workmux

Throw tmux in and this is my exact setup as well. I'm looking into finding ways to orchestrate entire workflows across multiple agents in a harness-agnostic way (locally at first).

Cmux is rather fancy if you still like a UI. Used to love iTerm but Cmux was perfect for tons of ClaudeCode/Codex instances.

Re: Ask HN: What is your (AI) dev tech stack / workflow?

#120

Post by alok-g »

sermakarevich wrote: post #25

I am using Spec Driven Development approach implemented as a Claude Code plugin since Feb for all mid + size tasks. The idea is to write detailed specs first using agent help doing research and interviewing, decompose the task into smaller subtasks, write detailed spec for each task, implement each task separately. You can restart the session after every step in the workflow and after each subtask implementation sinc…

I would love to see examples for various types of specs written, as in actual texts of the specs for various types of it.

It would also help to understand how are changes to specs handled? Is the agent given both old and new versions to figure out the updates needed?

Thanks.

Post reply on HN