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

September 21, 2026

AI Summary

5 min read

Zach Lloyd, CEO of Warp, is building what he calls a "software factory"—a system that turns ideas into shipped code through a centralized, cloud-based set of agents, MCP servers, and configuration, all defined in code. In a recent month, Warp shipped over 2,000 pull requests this way. The factory doesn't just write code; it handles triage, issue tracking, implementation, code review, QA with computer-use verification, and merging—all kicked off from a public Slack channel. The result is a shift from individual, local coding sessions to a visible, measurable, and improvable production line for software.

The factory: from local agent to centralized production line

The core difference between a coding agent and a factory is that the factory is a comprehensive, defined system that manages the entire software development lifecycle, not just the coding step. At Warp, this system is named Wilson. A builder—engineer, designer, or product person—can tag Wilson in a public Slack channel with a task. Wilson then opens a Linear issue, implements the change, creates a GitHub PR, runs computer-use QA (producing a video of the completed feature), and merges it. The entire process is public, visible to the whole team, and integrated across Slack, Linear, and GitHub. Work can also be initiated automatically by external systems like Sentry crash reports.

Continue reading the full summary in the app — free to try.

Read Full Summary →

Free • No credit card required

Listen to Audio Summary Open in App

Never miss an episode of How I AI

Get every new episode summarized in your inbox — free, ~5 minutes to read.

No spam. Unsubscribe anytime.

What you'll learn

1 (00:00) **The 35-Minute PR vs. the 3.5-Hour Human Review** - Claire opens with a provocative observation: Warp ships 2,000 PRs a month, but the human review step takes 3.5 hours—making humans the bottleneck.
2 (02:35) **What is a Software Factory?** - Zach explains the factory as a way to harness agents in an organized manner to build software from ideas, moving beyond simple coding agents.
3 (08:03) **From Builder to Manager: The Factory as a CTO's Dream** - The factory's real power is not just for individual builders but for managers who need visibility and control over the entire development process.
4 (14:44) **Humans Are the Bottleneck: Code Review and Risk Management** - Claire challenges Zach on the 3.5-hour human review delay, leading to a discussion on how to manage code review in a high-PR-volume world.
5 (17:07) **Cost, Models, and the Factory's Centralized View** - Zach shows the factory's cost dashboard, demonstrating how centralized data enables optimization.
6 (19:18) **Scoring and the Self-Improvement Loop** - The factory uses a scoring system with LLM-as-a-judge to evaluate every agent run across dimensions like "redundant tests."
7 (25:59) **The Summary: Public Work, Aggregate Analysis, and Session-Level Telemetry** - Claire summarizes the key themes of the factory approach.

+ Full timestamped outline available in the app

Guests on this episode

Zach Lloyd

Show Notes

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.

In this episode:

Why a software factory is more than a coding agent
The public Slack → Linear → GitHub → QA workflow
Human interactions per PR as a signal of automation and throughput
Why human review is still the bottleneck
Scoring agent runs, finding failure modes, and self-improving agent workflows
Replaying real tasks to choose model cost and quality tradeoffs
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) Intro

(02:35) Warp’s AI software factory, Wilson

(09:23) Automatic factory triggers

(11:12) The engineering leader dashboard Zach wishes he’d had

(15:18) How code review is changing in an AI factory

(17:08) Tracking cost per PR across model configs

(18:47) Using LLM-as-a-judge to score every agent run

(20:02) Catching redundant tests

(22:19) How the factory self-improves from failed runs

(26:03) Quick recap

(28:33) Building a cost-quality Pareto chart for model selection

(31:35) How Zach uses AI for non-technical CEO work

(32:10) Figma MCP demo

(35:43) Granola MCP demo

(36:41) GOG CLI demo

(38:20) Thinking in parallel tasks instead of sequential ones

(40:42) Zach’s prompting strategy for factory tasks

(44:48) Where to find Zach

—

Tools referenced:

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

• Warp Factories: https://warp.dev/factories

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

• GitHub (version control and PR management):