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

2026-03-23 · Source: Lenny's Newsletter · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering, FinTech & Digital Financial Services · Depth: Intermediate, quick

Summary

Stripe software engineer Steve Kaliski details "minions," the company's internal AI coding agents that generate approximately 1,300 pull requests weekly with minimal human oversight beyond code review. Kaliski demonstrates how engineers initiate development tasks from Slack, utilizing cloud-based development environments to facilitate parallel agent workflows. The discussion highlights the importance of a positive developer experience for both human and AI agents, and the critical role of cloud environments in accelerating AI-powered engineering. A key innovation presented is machine-to-machine payments, enabling AI agents to autonomously transact with third-party services to accomplish tasks, such as planning a birthday party using Claude and various tools. The system also allows non-engineers at Stripe to use minions for code-related tasks.

Key takeaway

For AI Architects and Product Managers evaluating AI agent integration, Stripe's "minions" demonstrate a viable path to dramatically increase engineering output. Your teams should prioritize robust cloud development environments and consider implementing machine payment protocols to empower agents with autonomous transaction capabilities, thereby expanding their operational scope beyond code generation to include real-world service interaction.

Key insights

Stripe's "minions" are AI coding agents that significantly boost development velocity through automation and machine payments.

Principles

• Developer experience benefits both human and AI agents.
• Cloud environments enable parallel AI engineering workflows.

Method

Stripe's minions are activated from Slack, operate in cloud development environments, and use an agent loop with system prompts. They leverage machine payment protocols for autonomous transactions with third-party services.

In practice

• Activate AI agents via simple interfaces like Slack emojis.
• Implement machine payment protocols for agent autonomy.
• Utilize cloud environments for scalable AI agent operations.

Topics

• AI Coding Agents
• Developer Productivity
• Machine Payments
• Cloud Development Environments
• AI Agent Orchestration

Code references

• block/goose

Best for: AI Architect, AI Product Manager, Entrepreneur, AI Engineer, Software Engineer, MLOps Engineer

Related on AIssential

• 🎙️ This week on How I AI: How Stripe built “minions”—AI coding agents that ship 1,300 PRs per week + How to turn Claude Code into your personal life operating system — Investments in developer experience and cloud environments significantly boost AI agent performance and adoption.
• How Stripe deploys 1,300 AI-written PRs per week — Stripe uses AI agents and cloud environments to automate engineering tasks and enable autonomous machine-to-machine payments.
• AI should help us produce better code — AI coding agents can enhance code quality and reduce technical debt by automating refactoring and enabling rapid prototyping.
• Presentation: Directing a Swarm of Agents for Fun and Profit — Orchestrating AI agent swarms enables rapid, cost-effective, and lower-carbon software development, shifting focus to platform engineering.
• The Rise of Cloud Coding Agents — Cloud-based AI coding agents enable asynchronous, autonomous development workflows, enhancing scalability over traditional desktop agents.
• How Stripe's "minions" write 1,300 pull requests per week with minimal human intervention — Automated documentation generation and preview streamline development workflows and enable parallel changes.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Lenny's Newsletter.