Remix.run Logo
Minions – Stripe's Coding Agents Part 2(stripe.dev)
75 points by ludovicianul 4 hours ago | 36 comments
Ozzie_osman 5 minutes ago | parent | next [-]

The challenge with all these builds is it's unclear whether, at some point, the models and tooling around them will just do this better. I guess at Stripe's scale, it might make sense to build in house, but, for the rest of us, we have to balance build vs. buy with much smaller teams. But, if we build we could end up being like companies who built their own web frameworks back in the day.

testfrequency 3 hours ago | parent | prev | next [-]

How is this already #1 on the front page with 12 upvotes and 9 comments…

The article doesn’t reveal much. It feels like a fluff piece, and I can’t comprehend what the goal of sharing “we use AI agents” means for the dev community, with little to no examples to share. For a “dev” micro blog, this feels very lackluster. Maybe the Minion could have helped with the technical docs?

EDIT: slightly adjusts tinfoil hat minutes later it’s at #6

netule 21 minutes ago | parent | next [-]

Stripe was launched through Y Combinator. It makes sense for their stuff to quickly bubble to the top of their news aggregator.

nylonstrung 2 hours ago | parent | prev | next [-]

It has all the trappings of NIH syndrome.

Reinventing the wheel without explaining why existing tools didn't work

Creating buzzwords ("blueprints" "devboxes") for concepts that are not novel and already have common terms

Yet they embrace MCP of all things as a transport layer- the one part of the common "agentic" stack that genuinely sucks and needs to be reinvented

throwaway-aws9 27 minutes ago | parent [-]

resume driven development

PunchyHamster 15 minutes ago | parent | prev | next [-]

well, it's very important, now you know the financial code is handled by a bunch of barely supervised AI tools and can make decisions on whether to use product or not based on that

BiteCode_dev 3 hours ago | parent | prev [-]

Likely they have whitelisted domaine names that go straight to the home page. Would make sense to put all Y combinator ex and new startup sites.

Marketting is a major goal of HN after all.

dewey 2 hours ago | parent | next [-]

Or the simpler explanation (which is probably closer to the truth): Stripe is a very popular company on HN as many people use them, their founders sometimes comment here and if they share their opinion on something people pay attention and upvote it.

nullstyle an hour ago | parent [-]

Or the even simpler explanation, that whenever Stripe posts a blog post, they have nine or 10 employees waiting to upvote it the moment it goes live.

handfuloflight 2 hours ago | parent | prev [-]

your absolut lee r8

_ache_ 9 minutes ago | parent | prev | next [-]

Why they is so many 404. Linked to mp3 ?! What was this feature ?

jimmydoe 2 hours ago | parent | prev | next [-]

This is a devops post. They just brag about the plumbing.

Dark secret of dark factory is high quality human input, which takes time and focus to draft up, otherwise human will end up multiple shot it, and read thru the transcript to tune the input.

3rodents 4 hours ago | parent | prev | next [-]

Are any companies doing this sharing the code being produced or some example Pull Requests? I am wondering if a lot of the human review is substantive or rubber stamping - as we see with long Pull Requests from humans. I know I would half-ass a review of a PR containing lots of robot code. I assume stripe has higher standards than me but would be nice to see some real world examples.

fnord123 4 hours ago | parent [-]

On thing that troubles me is that code reviews are also an educational moment for seniors teaching juniors as well as an opportunity for people who know a system to point out otherwise undocumented constraints of the system. If people slack on reviews with the agent it means these other externalities suffer.

Are being handling this at all? Is it no longer needed because it gets rolled into AGENTS.md?

blitzar 3 hours ago | parent | next [-]

I find working with Ai a lot like working with a junior employee... with the junior employee they learn and get better (skill level and at dealing with me) but with Ai the mentoring lessons reset once you type /clear

Skills are a positive development for task preferences, agents.md for high level context, but a lot of the time its just easier to do things the way your Ai wants.

yunohn an hour ago | parent | prev [-]

> educational moment for seniors teaching juniors

You see, this is no longer necessary - companies are firing all the non-seniors, are not hiring any juniors, and delegating everything to AI. This is the future apparently!

gas9S9zw3P9c 4 hours ago | parent | prev | next [-]

Where is the detail? Examples? Something concrete? I don't think it is, but it does read like LLM generated content marketing. Lots of generic statements everyone knows. Yes, dev environments are helpful. Have been for 20 years. Yes, context and rules are important for agents. Surprise.

TLDR "look we use AI at Stripe too, come work here"

nottorp 3 hours ago | parent | prev | next [-]

Hey can they ask their coding agents to support 3D secure, so I can pay with EU emitted credit cards on the few US sites I'm interested in?

lmz an hour ago | parent [-]

That's for the Stripe customer to configure. Stripe itself has supported 3DS since ages ago.

Edit: also you'll find a pretty common sentiment among US website owners is that the new API that supports 3DS is overcomplicated and they want their 7 lines of code create-a-charge-with-a-token back. Screw the Europeans because they only care about US buyers anyway.

rco8786 3 hours ago | parent | prev | next [-]

I'm sure there are lots of Stripe engineers that cruise the comments here. Anyone care to provide some color on how this is actually working? It's not a secret that agents can produce tons and tons of code on their own. But is this code being shipped? Maintained? Reviewed?

etothet 2 hours ago | parent | next [-]

Part 1 is linked in this article and explains a bit: “Minions are Stripe’s homegrown coding agents. They’re fully unattended and built to one-shot tasks. Over a thousand pull requests merged each week at Stripe are completely minion-produced, and while they’re human-reviewed, they contain no human-written code.”

I could be wrong, but my educated guess is that, like many companies, they have many low hanging fruit tasks that would never make it into a sprint or even somewhat larger tasks that are straight forward to define and implement in isolation.

dakolli 3 hours ago | parent | prev [-]

The few guys who they haven't laid off are too busy reviewing and being overworked, doing the work of 10 to scroll HN. Gotta get their boss another boat, AI is so awesome!

malfist 2 hours ago | parent [-]

Stripe hasn't had a layoff in a good while. Stripe is hiring like mad and is planning on growing engineering significantly. Your comment isn't grounded in reality

co_king_5 an hour ago | parent [-]

If you apply to work at Stripe, your job could be fixing the AI bullshit described in the article!

vbs_redlof 4 hours ago | parent | prev [-]

Good to see we're vibe coding critical financial infrastructure. Progress is being made.

Next up: let's vibe code a pacemaker.

trevorhinesley 3 hours ago | parent | next [-]

The glass-half-full here is it’s an incredible signal that one of the largest financial gateways in the world is _able_ to do this with current capabilities.

Personally, this is exciting.

handfuloflight 3 hours ago | parent | next [-]

They are enforcing rigor, on agents, the same way they would on humans. Do people think Stripe's engineering team would have been able to progress if each individual (human | machine) employee was not under harness and guardrail, and just wrote code willy nilly according to their whims? Vibe coding is whimsical, agentic engineering is re-applying what brought and brings rigor to software engineering in general, just to LLM outputs. Of course, it's not only that and there are novel problem spaces.

dakolli 3 hours ago | parent [-]

bot ass comment.

handfuloflight 3 hours ago | parent | next [-]

You're absolutely wrong! @dang, I really did write each letter by hand!

Lt. Dang, ice cream!

stareatgoats an hour ago | parent | prev [-]

Isn't there a rule against this - i.e. accusing commenters for using LLMs (the offensive language aside)? Implicitly there is [0], because I can't see how it adds to the conversation. So what if it sounds like an LLM? Soon you won't be able to tell the difference anyway, and all that will be left is some chance that you are correct. Comments should be judged their content merits, not on whether the commenter is native English speaker or not.

[0] > Be kind. Don't be snarky. Converse curiously; don't cross-examine. Edit out swipes. Comments should get more thoughtful and substantive, not less, as a topic gets more divisive. When disagreeing, please reply to the argument instead of calling names. "That is idiotic; 1 + 1 is 2, not 3" can be shortened to "1 + 1 is 2, not 3." Don't be curmudgeonly. Thoughtful criticism is fine, but please don't be rigidly or generically negative.

etc: https://news.ycombinator.com/newsguidelines.html

handfuloflight 27 minutes ago | parent [-]

What can I say? I speak like my friends.

kypro 3 hours ago | parent | prev [-]

Exactly, 1000 PRs per week probably equates to around ~100 engineers worth of output.

Hard to do an exact ROI, but they're probably saving something like $20,000,000+ / year from not having to hire engineers to do this work.

qudat 3 hours ago | parent | next [-]

They still need someone to review and hopefully QA every PR. I doubt it’s saving much time except maybe the initial debug pass of building human context of the problem. The real benefit here is the ability for the human swe to quickly context switch between problems and domains.

But again: the agent can only move as fast as we can review code.

echelon 38 minutes ago | parent | prev [-]

And they're not the only company doing this.

Financial capital at scale will begin to run circles around labor capital.

ndr 3 hours ago | parent | prev | next [-]

Soon indeed. From today:

> Cardiologist wins 3rd place at Anthropic's hackathon.

https://x.com/trajektoriePL/status/2024774752116658539

handfuloflight 3 hours ago | parent | prev [-]

Vibe coders do not know what linting is.