How Stripe built “minions”—AI coding agents that ship 1,300 PRs weekly from Slack reactions | Steve Kaliski (Stripe engineer)

**Steve Kaliski** (0:00)
At Stripe, we're landing about 1,300 PRs that have no human assistance besides review per week. A lot of where our work begins is, it could be in a Google Doc as we're planning a new feature, or maybe a GR ticket comes in, or we're talking about something in Slack. I can click an emoji, and then the menu will sort of attempt to one-shot resolving that prompt using all the tools that are available at Stripe.

**Claire Vo** (0:19)
When you're in larger organizations, there's so much friction that can come between a good idea and getting it into the world.

**Steve Kaliski** (0:26)
Not only can I have one of these, but I could have many, many of these running in parallel in isolated environments, making isolated changes all at the same time.

**Claire Vo** (0:33)
How are you getting all this code review done?

**Steve Kaliski** (0:35)
Whether the text has been written by Steve or the text has been written by Steve's robot, you still want that CI environment that's providing confidence that the code that's being changed is safe, and that as it rolls out, we're having blue-green deployment so you can roll back to. All that is super critical, independent of the nature of the authoring of it.

**Claire Vo** (0:52)
No matter how juiced these laptops are, you get three or four work trees in, and it starts to sound like an airplane taking off. It's no good. And so I do think on this multi-threading, agentic engineering work, cloud environments and virtual environments are so important to unlock velocity.
Welcome back to How I AI. I'm Claire Vo, product leader and AI obsessive, here on a mission to help you build better with these new tools. Today we have Steve Kaliski, a software engineer at Stripe, and he's going to show us how the Stripe team deploys a bunch of minions to do their engineering work. We'll also watch an agent spend a little bit over $5 to plan a birthday party all in Claude code. Let's get to it. This episode is brought to you by Optimizely. Most marketing teams aren't short on ideas, but what they are short on is time. And that's exactly what Optimizely Opal gives you back. With AI agents that handle real marketing workflows. You know, like creating content and checking compliance, generating experiment variations, personalizing user experiences, analyzing pages for GEO, even tasks like approvals and reporting. It's your AI agent orchestration platform for marketing and digital teams. Plugging seamlessly into the tools you already use, handling the boring busy work, and keeping everything on brand. That leaves marketers with more time to do your actual job. See what Opal can automate for your team by signing up for a free enterprise agentic AI workshop with Optimizely. Find out more at optimizely.com/how I AI. Attend live and you'll get a free pair of Ray-Ban Meta AI glasses. Steve, I'm so excited to have you on How I AI because I saw the Stripe Minions on the timeline. And one, exceptional branding, don't sue us. And two, I just love the idea that you and your colleagues in the team at Stripe have created not just one agent, but minions all across the company that can help with development work. And I'm so excited for you to show us how that helps you in your day to day here. So welcome to How I AI.

**Steve Kaliski** (3:12)
Thank you for having me.

**Claire Vo** (3:13)
So tell me, what has been the effect that minions have had on you personally at Stripe and at the Stripe team as a whole? Sure.

**Steve Kaliski** (3:22)
So for me personally, I think sort of anecdotally, I don't remember the last time I started work in the text editor. So I do end up there often. But what I found is that a lot of where our work begins is, it could be in a Google Doc as we're planning a new feature, or maybe a GR ticket comes in, or we're talking about something in Slack. And those are the more natural entry points to starting work. And then you end up in a text editor when it's time to actually do the work or make the final tweak. And it just felt very natural. And I think in particular, the activation energy of starting work feels a lot lower. So if you're in a Slack thread and maybe there's a piece of user feedback and it's something simple like we have to update the docs or maybe it's something more consequential and we just want to build a prototype, I can click an emoji and the work begins. And often the work finishes too. We're landing about 1300 PRs that have no human assistance besides review per week.