AI Summary
5 min readClaire, the host of How I AI, opens with a blunt diagnosis: teams that have embraced AI-generated code are now drowning in pull requests. The old rule—every PR needs a human review—is collapsing under volume. Her solution, inspired by engineering teams at Intercom and Rewind, is to build a PR review bot that scores risk and auto-approves low-risk changes, leaving humans to focus only on the handful of PRs that genuinely need their judgment. She walks through building one in about 30 minutes using Vercel's Eve framework, with Codex doing most of the heavy lifting.
Why auto-approve PRs at all?
The instinct to review every AI-written PR is strong, but Claire argues it is both unnecessary and counterproductive. She points to Intercom's published metrics: AI-approved PRs were approved five times faster than human-reviewed ones, and the revert rate (code that had to be fixed after hitting production) was lower for AI-written code than for human-written code. The key insight is that AI can be an advantage for safety and quality, not a liability—provided you build the right guardrails.
Continue reading the full summary in the app — free to try.
Read Full Summary →Free • No credit card required
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 PR Review Crisis: Why You're Drowning** - Claire introduces the core problem: AI-generated PRs are flooding engineering teams, and human review can't keep up.
- 2 (01:25) **Sponsor Break: WorkOS** - Brief sponsored segment on enterprise authentication and access control APIs.
- 3 (02:35) **The Case for AI-Approved PRs** - Claire addresses the common objection that all PRs must be human-reviewed, citing Intercom's proven approach.
- 4 (04:53) **Inspiration from Intercom and Rewind** - Two key blog posts that shaped the approach to building the PR review bot.
- 5 (06:12) **Why Vercel Eve? The Agent Framework Choice** - Claire explains why she chose Eve over other agent frameworks for this project.
- 6 (08:14) **The Chat SDK and Eve's Ease of Use** - How the underlying Chat SDK simplifies multi-channel bot development.
- 7 (09:16) **Building the Bot: One-Shot Prompting in Codex** - How Claire created the entire bot with a single prompt and minimal iteration.
+ Full timestamped outline available in the app
Show Notes
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.
What you’ll learn:
- Why AI-generated PRs create a review bottleneck and why the answer isn’t reviewing all of them
- How Intercom 5x’d PR approval speed and reduced revert rates by putting AI in the review loop
- Why Vercel Eve is the simplest framework I’ve found for deploying AI agents in Slack and GitHub
- How I built a full PR review agent in Codex with one prompt and a few steering turns
- The six components I use to score PR risk (blast radius, reversibility, data security, ops impact, verification gap, and change surface)
- How I used Chrome browser use to handle Slack bot and GitHub app configuration so I never had to click through setup screens manually
- Why auto-approved PRs can be SOC 2 compliant as long as the process is auditable, queryable, and in your risk policy
- How to set up Slack escalation so low-risk PRs become a two-click merge with no manual review
—
Brought to you by:
WorkOS—Make your app Enterprise Ready today
—
In this episode, we cover:
(00:00) The PR review backlog problem nobody’s talking about
(02:35) Why you don’t have to review every AI-generated PR
(05:14) How Intercom built AI-approved PRs (and proved they’re safer)
(06:10) How the Eve framework works (directory, skills, channels, connectors)
(09:16) The Codex prompt I used to build the entire bot
(11:36) What the agent actually does: read, score, approve, or escalate
(13:07) Setting up your Eve agent
(15:47) The six-component risk scoring model
(17:23) Merge Mommy in action: three live PR examples
(21:10) Recap and how to build your own version
—
Tools referenced:
• Vercel Eve: https://vercel.com/eve
• Vercel AI SDK: https://sdk.vercel.ai/
• Vercel Chat SDK: https://chat-sdk.dev/
• Codex (OpenAI): https://openai.com/codex
—
Other references:
• AI is ap
More from this podcast
How I AI →