How Companies Actually Run AI Agents: Stripe Merges 1,300+ PRs a Week With No Hand-Written Code
iamrobotbear · x · 2026-08-19
A long thread by @undefinedKi rounds up the most useful yet buried sources on how companies really operate AI agents:
- Stripe: its coding agents merge over 1,300 PRs a week with zero human-written code; a Slack message spins up an isolated machine in seconds, humans only review.
- Vercel: removing 80% of its agent's tools yielded more than any model upgrade.
- METR: PRs that pass SWE-bench are 24.2 points less likely to be merged by a human, a gap growing every year.
- OpenAI: the canonical post that named the field, by the engineer whose team shipped a million lines without hand-writing code.
The thread also points to the article How to Design an Agent Harness, covering six decisions that turn a model into a worker you can leave alone.
More from coding & agent
- Dev Audit Practice: Complementing Git with Artifact Scans — philrox_ · 2026-08-20
- Open-Source Full-Stack AI Template: FastAPI + Next.js with Agents and RAG — tom_doerr · 2026-08-20
- MLX Swift inference engine improvements to be ported open-source; run local Qwen via built-in LM server — gajesh · 2026-08-20
- DeepSeek Plugin Monitor: Growth Slows, 177 Added Daily — vista8 · 2026-08-20
- Agent Experience Engineering: designing products LLMs want to use — eptwts · 2026-08-20
- Agents evolving into 'directories' with runtime as infrastructure — hwchase17 · 2026-08-20