Build an AI code review bot in 30 minutes with Vercel Eve

<p>AI writes most of my code now, and that created a new problem: a PR queue I couldn’t keep up with. In this episode, I walk through how I built Merge Mommy, a Vercel Eve agent that reads every PR after checks pass, scores it across six risk dimensions, auto-approves the low-risk ones, and pings me in Slack for anything that needs a human. I built the whole thing in one Codex session, it’s SOC 2 compatible, and it’s already cleared my backlog.</p><p><br /></p><p><strong>What you’ll learn:</strong></p><ol><li>Why AI-generated PRs create a review bottleneck and why the answer isn’t reviewing all of them</li><li>How Intercom 5x’d PR approval speed and reduced revert rates by putting AI in the review loop</li><li>Why Vercel Eve is the simplest framework I’ve found for deploying AI agents in Slack and GitHub</li><li>How I built a full PR review agent in Codex with one prompt and a few steering turns</li><li>The six components I use to score PR risk (blast radius, reversibility, data security, ops impact, verification gap, and change surface)</li><li>How I used Chrome browser use to handle Slack bot and GitHub app configuration so I never had to click through setup screens manually</li><li>Why auto-approved PRs can be SOC 2 compliant as long as the process is auditable, queryable, and in your risk policy</li><li>How to set up Slack escalation so low-risk PRs become a two-click merge with no manual review</li></ol><p>—</p><p><strong>Brought to you by:</strong></p><p><a href="https://workos.com/?utm_source=lennys_howiai&amp;utm_medium=podcast&amp;utm_campaign=q22025" rel="ugc noopener noreferrer" target="_blank">WorkOS</a>—Make your app Enterprise Ready today</p><p>—</p><p><strong>In this episode, we cover:</strong></p><p>(00:00) The PR review backlog problem nobody’s talking about</p><p>(02:35) Why you don’t have to review every AI-generated PR</p><p>(05:14) How Intercom built AI-approved PRs (and proved they’re safer)</p><p>(06:10) How the Eve framework works (directory, skills, channels, connectors)</p><p>(09:16) The Codex prompt I used to build the entire bot</p><p>(11:36) What the agent actually does: read, score, approve, or escalate</p><p>(13:07) Setting up your Eve agent</p><p>(15:47) The six-component risk scoring model</p><p>(17:23) Merge Mommy in action: three live PR examples</p><p>(21:10) Recap and how to build your own version</p><p>—</p><p><strong>Tools referenced:</strong></p><p>• Vercel Eve: <a href="https://vercel.com/eve" rel="ugc noopener noreferrer" target="_blank">https://vercel.com/eve</a></p><p>• Vercel AI SDK: <a href="https://sdk.vercel.ai/" rel="ugc noopener noreferrer" target="_blank">https://sdk.vercel.ai/</a></p><p>• Vercel Chat SDK: <a href="https://chat-sdk.dev/" rel="ugc noopener noreferrer" target="_blank">https://chat-sdk.dev/</a></p><p>• Codex (OpenAI): <a href="https://openai.com/codex" rel="ugc noopener noreferrer" target="_blank">https://openai.com/codex</a></p><p>—</p><p><strong>Other references:</strong></p><p>• AI is approving our pull requests: Here’s how we made it safe:<a href="https://www.intercom.com/blog/ai-is-approving-our-pull-requests-heres-how-we-made-it-safe/" rel="ugc noopener noreferrer" target="_blank"> https://www.intercom.com/blog/ai-is-approving-our-pull-requests-heres-how-we-made-it-safe/</a></p><p>—</p><p><strong>Where to find Claire Vo:</strong></p><p>ChatPRD: <a href="https://www.chatprd.ai/" rel="ugc noopener noreferrer" target="_blank">https://www.chatprd.ai/</a></p><p>Website: <a href="https://clairevo.com/" rel="ugc noopener noreferrer" target="_blank">https://clairevo.com/</a></p><p>LinkedIn: <a href="https://www.linkedin.com/in/clairevo/" rel="ugc noopener noreferrer" target="_blank">https://www.linkedin.com/in/clairevo/</a></p><p>X: <a href="https://x.com/clairevo" rel="ugc noopener noreferrer" target="_blank">https://x.com/clairevo</a></p><p>—</p><p>Production and marketing by <a href="https://penname.co/" rel="ugc noopener noreferrer" target="_blank">https://penn