How Stripe built “minions”—AI coding agents that ship 1,300 PRs weekly from Slack reactions | Steve Kaliski (Stripe engineer)
· Summarized
Key takeaways
- Stripe's AI minions significantly reduce the coding workload by automating PR submissions.
- Lowering activation energy enhances productivity in tech organizations, allowing ideas to move from concept to execution rapidly.
- Investing in developer experience positively impacts both human engineers and AI agents.
- Cloud environments are essential for unlocking parallel workflows and improving overall engineering velocity.
- Machine payments show the practical application of AI, allowing agents to autonomously transact and solve problems.
Summary
Introduction to Stripe's AI Minions
Steve Kaliski, a software engineer at Stripe, discusses 'minions'—AI coding agents created to streamline the development process at Stripe. These agents now ship around 1,300 pull requests (PRs) weekly, drastically reducing the friction typically faced in larger organizations between a good idea and its implementation.
Activation Energy and Developer Experience
The conversation emphasizes the importance of 'activation energy' in starting code projects. Using tools like Slack, the engineers can initiate work quickly with minimal barriers. Lowering this activation energy not only boosts productivity for human engineers but also improve outcomes for AI agents.
Minion Architecture and Functionality
Steve explains how Stripe's developers interact with the minions, leveraging cloud environments and hosted development setups. The use of emojis in Slack to activate a minion illustrates how user-friendly the system is.
Benefits of Developer Experience
A strong developer experience is crucial for both human programmers and AI agents. By investing in quality tools and resources for engineers at Stripe, the company creates a virtuous loop in which good developer experiences lead to better agent performance.
Machine Payments and Agent Economic Transactions
Steve showcases a demo where AI agents autonomously conduct financial transactions to accomplish tasks. This segment highlights the practicality of AI in everyday business operations, including booking services and making transactions without human intervention.
Code Review Strategies for AI-Generated Work
Kaliski discusses the strategy for managing code reviews for the thousands of PRs generated by AI agents. With strong CI environments and test coverage in place, confidence in the safety and effectiveness of the AI-generated code remains high.
Future Implications of AI in Software Development
Toward the end, Kaliski speculates on the future of software engineering, where non-technical team members may also engage with AI coding agents. This opens new avenues for efficiency and innovation within businesses.
Sponsors
- Optimizely · Your AI agent orchestration platform for marketing and digital teams
- Rippling · Stop wasting time on admin tasks, build your startup faster
Show notes
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:
- How Stripe’s “minions” write 1,300 pull requests per week with minimal human intervention
- Why a good developer experience for humans creates better outcomes for AI agents
- The critical role of cloud development environments in unlocking AI-powered engineering velocity
- The machine payment protocol that lets AI agents spend money to accomplish tasks
- The code review strategy for handling thousands of agent-written PRs
- Why non-engineers at Stripe are starting to use minions to ship code
- 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/
—
Production and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email jordan@penname.co.
Follow this show on AudioBrevity and new episodes get summarized for you. Create a free account