Is this not a bash script, but run through a "maybe it won't work this time" randomizer?<p>Sometimes I feel like I live on another planet. Wouldn't you at least get Claude to write the bash script, confirm it works how you like, then run that? Why get an LLM to guess how to do it each and every time?<p>At least they are still manually approving, which the title made sound like something they'd move on from.
We have a very small team and release at will. Some days multiple times, sometimes days between.<p>We don't use AI, just have a well tested codebase and basic bash script automation mixed in with GitHub actions.<p>Not bashing AI tools in particular, but just learning some basic decades old tooling and processes gets you pretty much all of the way there.
> less manual work is always better.<p>Why do your releases involve non negligible manual work?<p>> We release 1-3 times per week.<p>If I were a customer, I would be concerned by this statement. Having an amateurish deployment strategy is one thing, but your release cadence implies low confidence and quality issues.
Is this a psyop to check how HN readers will react to this insanity ?
This could be a simple script. It <i>should</i> be a simple script. Please update us when this fails :)
The author of this article is using AI to run certain console commands, while still requiring them to manually advance the release process.<p>Almost as if the author does not know how to write a bash script, and reverted to using an AI prompt in stead?
I’ll be honest this sounds like something that could be completely automated without AI. Wouldn’t a simple shell script accomplish this? Merge, push tag, deploy release with tag. I’m really not sure why AI is useful here at all but maybe I’m missing something?
I just spent a day resurrecting an old iOS music app of mine that got kicked out of the app store because I didn't make time to keep up with changes and devices, and some music students kept asking "when is it going to get back on the app store?".<p>I used Claude Code in "do whatever you need to to modernize this code" mode for a bit and then went about correcting the things it got wrong. Many changes made were mechanical and useful and a few incorrect. It botched up some core code big time with changes that didn't make any sense, and I had to revert and micromanage changes to that. In all, it was a win for a day's work during the weekend.<p>Approx $30 well spent, but I give my thanks to the OSS community whose code made Claude Code possible and wish I could've split that with them.<p>The fact that software systems are architected with tons of mini languages means LLMs can be of use to select from the space of possibilities without me having to learn incidental details I don't want to spend time or my neurons on.
Fortunately I wasn't in the market for an AI shopping assistant anyhow, but still thanks for letting me know what to avoid if I ever became interested in one.
Please ask the agent to help write a workflow script (GitHub Actions yaml or makefile or similar) instead of using it as a runner - if you do that the release pipeline changes with each execution. You do not want a non deterministic release pipeline that's mostly correct. You want one that's checked in to version control and always does exactly the same thing, with all logs and artefacts recorded.<p>By all means use whatever AI agent you have to help set that up.
Speaking of which - I was wondering if there is a catalogue of release processes? Variety, usual steps, checklists?<p>Asking because development processes are a hot market themselves think of XP, Scrum, agile etc so wondering if there's something documented about release processes.
RemindMe! 3 months from now.<p>Willing to put down a little bit of my money that this is going to blow up in their faces in the near future.<p>I'm not super technical at all, but I don't understand why a team that does 1-3 deploys a week is not fully automating with "proper" CI.
> So please:<p>> 1. Check if there exists a release PR already. When you check, do not grep, just list ALL PRs.<p>Why would you make AI do this when you can just do it with an api call or git.<p>Does the author not know that there is a chance that it won't actuall list ALL PRs just because he put that in all caps?<p>we have lost our collective minds that this person is proudly publishing this stupidity to the world. i hate this so much.<p>can we pls ban these coders from the industry :(
This is cool and all, but I don't see why this can't be accomplished (and more deterministically) with a bunch of bash/python scripts. I've seen that done and work well in several firms for decades.
I mean, it's cute, but how the heck this is this an actual solution.<p>This is basic automation and a pretty weird deployment process that could literally be a proper ci/cd pipeline.
Letting AI control software releases might seem risky, but it may not be as problematic as it sounds—especially if you also use AI to handle issue support. :)