cd /news/ai-agents/how-warp-ships-2000-prs-a-month-with… · home topics ai-agents article
[ARTICLE · art-135849] src=lennysnewsletter.com ↗ pub= topic=ai-agents verified=true sentiment=↑ positive

How Warp ships 2,000 PRs a month with AI factories | Zach Lloyd (CEO, Warp)

Warp, the AI-powered terminal and software factory platform led by co-founder and CEO Zach Lloyd, ships 2,000 pull requests a month through its cloud-based software factory, which runs a Slack → Linear → GitHub → QA workflow from idea to merged PR. Lloyd said human review remains the bottleneck, and Warp scores every agent run with LLM-as-a-judge while tracking cost per PR across model configurations to build a cost-quality Pareto chart for model selection.

by read2 min views2 publishedSep 21, 2026
How Warp ships 2,000 PRs a month with AI factories | Zach Lloyd (CEO, Warp)
Image: Lennysnewsletter (auto-discovered)

Zach Lloyd is the co-founder and CEO of Warp, an AI-powered terminal and software factory platform used by tens of thousands of engineers. Before Warp, he spent nearly a decade at Google, including time as a principal engineer on Google Sheets. He built Warp from the ground up as a modern, AI-native alternative to legacy terminals, and the team has since expanded into software factories: a full cloud-based system that takes an idea in Slack all the way through to a merged PR.

Listen or watch on YouTube, Spotify, or Apple Podcasts

In this episode:

  1. Why a software factory is more than a coding agent
  2. The public Slack → Linear → GitHub → QA workflow
  3. Human interactions per PR as a signal of automation and throughput
  4. Why human review is still the bottleneck
  5. Scoring agent runs, finding failure modes, and self-improving agent workflows
  6. Replaying real tasks to choose model cost and quality tradeoffs
  7. CEO workflows with Figma MCP, Granola, and research agents

Brought to you by:

DX—Engineering intelligence for the AI era OpenArt—An all-in-one AI creation platform for images, videos, music, audio, and more

In this episode, we cover:

([00:00](https://www.youtube.com/watch?v=4_SHhSMHzNo)) Intro

([02:35](https://www.youtube.com/watch?v=4_SHhSMHzNo&t=155s)) Warp’s AI software factory, Wilson

([09:23](https://www.youtube.com/watch?v=4_SHhSMHzNo&t=563s&pp=0gcJCWMAwfN6Pr3D)) Automatic factory triggers

([11:12](https://www.youtube.com/watch?v=4_SHhSMHzNo&t=672s)) The engineering leader dashboard Zach wishes he’d had

([15:18](https://www.youtube.com/watch?v=4_SHhSMHzNo&t=918s)) How code review is changing in an AI factory

([17:08](https://www.youtube.com/watch?v=4_SHhSMHzNo&t=1028s)) Tracking cost per PR across model configs

([18:47](https://www.youtube.com/watch?v=4_SHhSMHzNo&t=1127s)) Using LLM-as-a-judge to score every agent run

([20:02](https://www.youtube.com/watch?v=4_SHhSMHzNo&t=1202s)) Catching redundant tests

([22:19](https://www.youtube.com/watch?v=4_SHhSMHzNo&t=1339s)) How the factory self-improves from failed runs

([26:03](https://www.youtube.com/watch?v=4_SHhSMHzNo&t=1563s)) Quick recap

([28:33](https://www.youtube.com/watch?v=4_SHhSMHzNo&t=1713s&pp=0gcJCWMAwfN6Pr3D)) Building a cost-quality Pareto chart for model selection

([31:35](https://www.youtube.com/watch?v=4_SHhSMHzNo&t=1895s)) How Zach uses AI for non-technical CEO work

([32:10](https://www.youtube.com/watch?v=4_SHhSMHzNo&t=1930s)) Figma MCP demo

([35:43](https://www.youtube.com/watch?v=4_SHhSMHzNo&t=2143s)) Granola MCP demo

([36:41](https://www.youtube.com/watch?v=4_SHhSMHzNo&t=2201s)) GOG CLI demo

([38:20](https://www.youtube.com/watch?v=4_SHhSMHzNo&t=2300s)) Thinking in parallel tasks instead of sequential ones

([40:42](https://www.youtube.com/watch?v=4_SHhSMHzNo&t=2442s)) Zach’s prompting strategy for factory tasks

([44:48](https://www.youtube.com/watch?v=4_SHhSMHzNo&t=2688s)) Where to find Zach

Tools referenced:

• Warp (AI terminal and software factories): [https://warp.dev](https://warp.dev)

• Warp Factories: [https://warp.dev/factories](https://warp.dev/factories)

• Linear (project and issue tracking): [https://linear.app](https://linear.app)

• GitHub (version control and PR management): [https://github.com](https://github.com)

• Slack (team communication and factory input layer): [https://slack.com](https://slack.com)

• Sentry (crash reporting and automated issue triggers): [https://sentry.io](https://sentry.io)

• Figma (design, used via Figma MCP): [https://figma.com](https://figma.com)

• Granola (AI meeting notes and MCP integration): [https://granola.so](https://granola.so)

• Grok Bot (fast inference, cost/quality trade-off): [https://x.ai/bot/guides/grok-bot-101](https://x.ai/bot/guides/grok-bot-101)

Where to find Zach:

X: https://x.com/ZachLloydTweets

Where to find Claire:

ChatPRD: [https://www.chatprd.ai/](https://www.chatprd.ai/)

Website: [https://clairevo.com/](https://clairevo.com/)

LinkedIn: [https://www.linkedin.com/in/clairevo/](https://www.linkedin.com/in/clairevo/)

Production and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email [email protected].

── more in #ai-agents 4 stories · sorted by recency
── more on @warp 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/how-warp-ships-2000-…] indexed:0 read:2min 2026-09-21 ·