How Stripe Deploys 1,300 AI-Written PRs per Week

How I AI
How I AIMar 25, 2026

Why It Matters

By automating routine code work at scale, Stripe shortens time‑to‑market and showcases a replicable model for AI‑augmented development that could reshape engineering productivity across the industry.

Key Takeaways

  • Stripe automates 1,300 weekly PRs using AI minions.
  • One‑click emoji triggers full development environment provisioning instantly.
  • AI agents handle code changes, testing, and CI without human coding.
  • Robust developer tooling boosts AI success and reduces activation energy.
  • Parallel isolated environments enable simultaneous multi‑threaded feature development.

Summary

Stripe’s engineering team has built a fleet of AI‑driven “minions” that automatically generate and land roughly 1,300 pull requests each week, with human involvement limited to code review. The system is triggered from everyday collaboration tools—Slack, Google Docs, or ticketing systems—by a simple emoji reaction, which launches a cloud‑hosted development environment, runs the necessary code modifications, and submits a PR for review.

The key to this velocity is the reduction of “activation energy”: engineers no longer need to spin up local environments, write boilerplate code, or manually run tests. The minions provision isolated cloud instances, configure repositories, execute Stripe’s extensive CI pipeline, and even perform blue‑green deployments, all while maintaining the same safety guarantees as human‑written code. Parallelism is baked in, allowing dozens of minions to operate simultaneously without interfering with each other.

Steve Khaliski emphasizes the cultural shift, noting, “When you’re in a Slack thread, I can click an emoji and the work begins, often finishing without me touching a line of code.” He also highlights the importance of Stripe’s mature developer tooling—internal documentation, code‑search utilities, and the open‑source Goose harness—that gives the agents the context they need to succeed. The system’s prompt engineering, he explains, is deliberately simple yet powerful, letting the AI navigate the massive codebase efficiently.

For the broader tech industry, Stripe’s approach demonstrates that large‑scale AI‑assisted development is feasible when paired with robust developer experience. Companies that invest in seamless dev environments and comprehensive internal docs can expect similar gains in speed, reduced coordination costs, and higher throughput, potentially redefining how software is built at scale.

Original Description

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: https://www.optimizely.com/howIAI
Rippling—Stop wasting time on admin tasks, build your startup faster: https://rippling.com/howiai
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/
• 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
Where to find Steve Kaliski:
Where to find Claire Vo:
_Production and marketing by https://penname.co/._
_For inquiries about sponsoring the podcast, email jordan@penname.co._

Comments

Want to join the conversation?

Loading comments...