How Stripe built “minions”—AI coding agents that ship 1,300 PRs weekly from Slack reactions | Steve Kaliski (Stripe engineer)
How I AI25 Mar

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

Steve Kaliski is a software engineer at Stripe who has spent the past six and a half years building developer tools and payment infrastructure. He’s part of the team that created “minions”—Stripe’s internal AI coding agents, which now ship approximately 1,300 pull requests per week with minimal human intervention beyond code review. In this episode, Steve demonstrates how Stripe engineers activate development work from Slack and leverage cloud-based development environments for parallel agent workflows, and demos machine-to-machine payments where AI agents transact autonomously with third-party services.


What you’ll learn:

  1. How Stripe’s “minions” write 1,300 pull requests per week with minimal human intervention
  2. Why a good developer experience for humans creates better outcomes for AI agents
  3. The critical role of cloud development environments in unlocking AI-powered engineering velocity
  4. The machine payment protocol that lets AI agents spend money to accomplish tasks
  5. The code review strategy for handling thousands of agent-written PRs
  6. Why non-engineers at Stripe are starting to use minions to ship code
  7. The future of software businesses built primarily for agent consumers

Brought to you by:

Optimizely—Your AI agent orchestration platform for marketing and digital teams

Rippling—Stop wasting time on admin tasks, build your startup faster

In this episode, we cover:

(00:00) Introduction to Steve

(02:39) Stripe’s minions and their effect on Stripe as a whole

(04:42) Why activation energy matters more than execution

(05:44) What is a minion? The technical architecture

(06:52) Demo: Activating a minion from Slack with an emoji

(09:04) Why good developer experience benefits both humans and agents

(11:22) Walking through the agent loop and system prompts

(13:42) Why Stripe chose Goose as their agent harness

(16:00) The role of Stripe’s developer productivity team

(17:15) Why cloud environments unlock multi-threaded AI engineering

(21:14) One-shot prompting: from Slack to shipped PR

(22:04) How Stripe handles code review for 1,300 AI-written PRs weekly

(23:44) Non-engineers using minions across the company

(24:53) Demo: Planning a birthday party with Claude and machine payments

(32:15) Quick recap

(35:08) The future of ephemeral, API-first businesses for agents

(36:36) Lightning round and final thoughts

Detailed workflow walkthroughs from this episode:

• How Stripe's AI 'Minions' Ship 1,300 PRs Weekly from a Slack Emoji: https://www.chatprd.ai/how-i-ai/stripes-ai-minions-ship-1300-prs-weekly-from-a-slack-emoji

• How to Build an Autonomous AI Agent That Pays for Services to Complete Tasks: https://www.chatprd.ai/how-i-ai/workflows/how-to-build-an-autonomous-ai-agent-that-pays-for-services-to-complete-tasks

• How to Automate Code Generation from a Slack Message into a Pull Request: https://www.chatprd.ai/how-i-ai/workflows/how-to-automate-code-generation-from-a-slack-message-into-a-pull-request

Tools referenced:

• Goose (AI agent harness): https://github.com/block/goose

• Claude Code: https://claude.ai/code

• Cursor: https://cursor.sh/

• VS Code: https://code.visualstudio.com/

• Slack: https://slack.com/

• Browserbase: https://browserbase.com/

• Parallel AI: https://www.parallel.ai/

• PostalForm: https://postalform.com/

• Stripe Climate: https://stripe.com/climate

Other references:

• Stripe machine payments: https://docs.stripe.com/payments/machine

• Blue-Green Deployment: https://martinfowler.com/bliki/BlueGreenDeployment.html

• Git worktrees: https://git-scm.com/docs/git-worktree

Where to find Steve Kaliski:

Twitter: https://twitter.com/stevekaliski

LinkedIn: https://www.linkedin.com/in/steve-kaliski-079a7710/

Where to find Claire Vo:

ChatPRD: https://www.chatprd.ai/

Website: https://clairevo.com/

LinkedIn: https://www.linkedin.com/in/clairevo/

X: https://x.com/clairevo

Production and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email jordan@penname.co.

Episoder(69)

“Farm-to-table software”: How I built a Thanksgiving party hub using Lovable for managing invites, dishes, shared recipes, and photos

“Farm-to-table software”: How I built a Thanksgiving party hub using Lovable for managing invites, dishes, shared recipes, and photos

In today’s pre-Thanksgiving episode, I walk you through how I vibe coded my very own “Thanksgiving party hub” using Lovable—and how I transformed it from AI-generated slop into something warm, persona...

19 Nov 202534min

“Nobody wanted to do this work”: How Emmy Award–winning filmmakers use AI to automate the tedious parts of documentaries

“Nobody wanted to do this work”: How Emmy Award–winning filmmakers use AI to automate the tedious parts of documentaries

Tim McAleer is a producer at Ken Burns’s Florentine Films who is responsible for the technology and processes that power their documentary production. Rather than using AI to generate creative content...

17 Nov 202547min

How this CEO turned 25,000 hours of sales calls into a self-learning go-to-market engine | Matt Britton (Suzy)

How this CEO turned 25,000 hours of sales calls into a self-learning go-to-market engine | Matt Britton (Suzy)

Matt Britton is the founder and CEO of Suzy, a consumer insights platform that has raised over $100 million in venture capital and works with top brands like Coca-Cola, Google, Procter & Gamble, and N...

10 Nov 202542min

The complete beginner’s guide to coding with AI: from PRD to generating your very first lines of code

The complete beginner’s guide to coding with AI: from PRD to generating your very first lines of code

This episode is for complete beginners. I walk you through how to build your very first coding project using AI tools—even if you’ve never written a line of code. Together, we’ll create a personal pro...

5 Nov 202545min

“Vibe analysis”: How Faire’s data team uses AI to investigate conversion drops, analyze experiment results, and convert raw data into executive-ready insights

“Vibe analysis”: How Faire’s data team uses AI to investigate conversion drops, analyze experiment results, and convert raw data into executive-ready insights

Tim Trueman and Alexa Cerf from Faire’s data team demonstrate how AI tools are revolutionizing data analysis workflows. They show how data teams, product managers, and engineers can use tools like Cur...

3 Nov 20251h 3min

Vibe-coding a kid-friendly AI fortune teller for your Halloween festivities | Marco Casalaina (Microsoft VP)

Vibe-coding a kid-friendly AI fortune teller for your Halloween festivities | Marco Casalaina (Microsoft VP)

In this impromptu Halloween special, Marco Casalaina (VP of Products for Core AI at Microsoft) demonstrates how he uses GitHub Spark to quickly build a mobile app that generates kid-friendly fortunes ...

31 Okt 202511min

“Cursor is a much better product manager than I ever was”: How this PM uses AI for PRDs, Jira tickets, and replying to coworkers | Dennis Yang (Chime)

“Cursor is a much better product manager than I ever was”: How this PM uses AI for PRDs, Jira tickets, and replying to coworkers | Dennis Yang (Chime)

Dennis Yang is the Principal Product Manager for Generative AI at Chime, where he’s pioneered AI workflows that meaningfully increase productivity. While most people use Cursor as a coding tool, Denni...

27 Okt 202550min

Claude Skills explained: How to create reusable AI workflows

Claude Skills explained: How to create reusable AI workflows

Today I dive into Anthropic’s latest feature that lets anyone create reusable workflows for Claude—no coding required. I break down exactly what Claude Skills are, how to build them from scratch, and ...

22 Okt 202527min

Populært innen Teknologi

lydartikler-fra-aftenposten
romkapsel
tomprat-med-gunnar-tjomlid
teknisk-sett
energi-og-klima
shifter
nasjonal-sikkerhetsmyndighet-nsm
teknologi-og-mennesker
smart-forklart
elektropodden
fornybaren
rss-impressions-2
rss-ai-forklart
pedagogisk-intelligens
rss-alt-som-gar-pa-strom
rss-heis
rss-polypod
rss-ki-praten
kortslutning
rss-grenser-for-ki