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

<p><strong>Zach Lloyd </strong>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.</p><p><br></p><p><strong>In this episode:</strong></p><ol><li>Why a software factory is more than a coding agent</li><li>The public Slack → Linear → GitHub → QA workflow</li><li>Human interactions per PR as a signal of automation and throughput</li><li>Why human review is still the bottleneck</li><li>Scoring agent runs, finding failure modes, and self-improving agent workflows</li><li>Replaying real tasks to choose model cost and quality tradeoffs</li><li>CEO workflows with Figma MCP, Granola, and research agents</li></ol><p>—</p><p><strong>Brought to you by:</strong></p><p><a href="https://getdx.com/howiai" target="_blank" rel="ugc noopener noreferrer"><strong>DX</strong></a>—Engineering intelligence for the AI era</p><p><a href="https://openart.ai/arena?utm_source=online&utm_medium=influencer&utm_campaign=infl-howiai-arena-na-acq-web" target="_blank" rel="noopener noreferer"><strong>OpenArt</strong></a>—An all-in-one AI creation platform for images, videos, music, audio, and more</p><p>—</p><p><strong>In this episode, we cover:</strong></p><p>(00:00) Intro</p><p>(02:35) Warp’s AI software factory, Wilson</p><p>(09:23) Automatic factory triggers</p><p>(11:12) The engineering leader dashboard Zach wishes he’d had</p><p>(15:18) How code review is changing in an AI factory</p><p>(17:08) Tracking cost per PR across model configs</p><p>(18:47) Using LLM-as-a-judge to score every agent run</p><p>(20:02) Catching redundant tests</p><p>(22:19) How the factory self-improves from failed runs</p><p>(26:03) Quick recap</p><p>(28:33) Building a cost-quality Pareto chart for model selection</p><p>(31:35) How Zach uses AI for non-technical CEO work</p><p>(32:10) Figma MCP demo</p><p>(35:43) Granola MCP demo</p><p>(36:41) GOG CLI demo</p><p>(38:20) Thinking in parallel tasks instead of sequential ones</p><p>(40:42) Zach’s prompting strategy for factory tasks</p><p>(44:48) Where to find Zach</p><p>—</p><p><strong>Tools referenced:</strong></p><p>• Warp (AI terminal and software fa