Skip to content
How I AIHow I AI

How Stripe deploys 1,300 AI-written PRs per week

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/ • 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._

Steve KaliskiguestClaire Vohost
Mar 25, 202641mWatch on YouTube ↗

CHAPTERS

  1. Stripe ships 1,300 AI-written PRs/week: what “minions” change

    Steve Kaliski opens with the headline metric: ~1,300 pull requests per week authored by AI with humans primarily doing review. Claire frames the core promise as reducing organizational friction so good ideas move to production faster.

  2. Lowering activation energy beats “better execution”

    They argue the biggest win isn’t raw coding speed but making it effortless to start. Minions let engineers (and eventually anyone) turn a casual Slack message into forward motion without context switching into heavy tooling first.

  3. What a “minion” is: devboxes + tools + an agent loop

    Steve explains the underlying architecture: Stripe already relies on hosted development environments because the codebase is too large to run locally. A minion provisions one of these environments, seeds it with a prompt, then iterates using Stripe’s internal tools to try to complete the task end-to-end.

  4. Demo: launching a minion from Slack via emoji reaction

    Steve demonstrates the “reaction-to-run” workflow in Slack: he posts a docs improvement request, adds a specific emoji reaction, and a minion is created on a new branch. The system provisions the environment, checks out code, configures services, and prepares preview capability automatically.

  5. Developer experience as agent experience (and vice versa)

    Claire highlights the feedback loop: strong human DX also makes agents more successful. Steve adds that “blessed paths” (clear docs and common workflows) prevent context-window blowups and raise the odds of one-shot success in a massive codebase.

  6. Inside the agent run: system prompt, to-dos, and Stripe MCP tooling

    They walk through the agent loop as it starts executing: locating relevant files, tracking its own tasks, making changes, and preparing commits. Claire notes the minimal system prompt (“Implement this task completely…”) and argues a solid harness can outperform overly engineered prompts.

  7. Why Stripe chose Goose as the agent harness

    Claire asks why Goose versus building from scratch or buying a commercial solution. Steve describes Goose as a base loop/harness they could fork and tailor to Stripe’s specific developer environment, while still offering engineers tools like Claude Code and Cursor alongside minions.

  8. The developer productivity team and cloud environments for parallelism

    Steve credits a long-standing developer productivity team for the infrastructure that makes minions possible. Claire emphasizes cloud/virtual dev environments as the unlock for “multi-threaded agentic engineering,” since local machines quickly become the limiting factor.

  9. One-shot prompting: from Slack request to a PR ready for human review

    They clarify what “one-shot” means: the human provides one prompt, then the agent loops internally until it can produce a completed implementation. The output is a PR that enters Stripe’s normal review process, with the agent handling the grind of setup, edits, and test iterations.

  10. Reviewing 1,300 AI PRs/week: CI, test coverage, and safe rollout

    Claire asks how Stripe keeps up with review volume. Steve argues time shifts from writing to reviewing, and that strong CI—tests, end-to-end synthetics, and safe deployment patterns like blue/green—creates confidence regardless of whether a human or robot authored the code.

  11. Minions beyond engineering: empowering non-engineers in Slack

    They discuss broader adoption: Slack as the universal interface lowers intimidation for non-engineers. Steve notes that product/design feedback is already “prompt-shaped,” so clicking an emoji to initiate a change or proof-of-concept can extend minions across functions.

  12. Agents as economic actors: planning a birthday party with machine payments

    Steve introduces a second theme: agents that can spend money to accomplish tasks by purchasing services on-demand. In a Claude Code demo, the agent researches a colleague’s interests, finds a venue, sends an invite via mail, and offsets emissions—using real paid API calls along the way.

  13. The future: ephemeral, API-first businesses built for agent customers

    They zoom out: many services may be consumed primarily through agents rather than human dashboards. Steve suggests new businesses can focus on a “hyper useful single API,” monetized directly for agent interactions, with wrappers and UX emerging later for humans.

  14. Lightning round: personal AI workflows and how Steve unblocks agents

    Steve shares personal use: rapidly prototyping small, disposable apps (e.g., kid-safe music controls) despite not knowing iOS development. When agents fail, he stays polite, asks them to explain/justify, and leaves “breadcrumbs” (diffs/status) to guide them—then saves repeatable prompts as reusable skills.

Get more out of YouTube videos.

High quality summaries for YouTube videos. Accurate transcripts to search & find moments. Powered by ChatGPT & Claude AI.

Add to Chrome