Skip to content
How I AIHow I AI

Build an AI code review agent with Vercel Eve (full tutorial)

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:* 1. Why AI-generated PRs create a review bottleneck and why the answer isn’t reviewing all of them 2. How Intercom 5x’d PR approval speed and reduced revert rates by putting AI in the review loop 3. Why Vercel Eve is the simplest framework I’ve found for deploying AI agents in Slack and GitHub 4. How I built a full PR review agent in Codex with one prompt and a few steering turns 5. The six components I use to score PR risk (blast radius, reversibility, data security, ops impact, verification gap, and change surface) 6. How I used Chrome browser use to handle Slack bot and GitHub app configuration so I never had to click through setup screens manually 7. Why auto-approved PRs can be SOC 2 compliant as long as the process is auditable, queryable, and in your risk policy 8. 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: https://workos.com?utm_source=lennys_howiai&utm_medium=podcast&utm_campaign=q22025 *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 approving our pull requests: Here’s how we made it safe: https://www.intercom.com/blog/ai-is-approving-our-pull-requests-heres-how-we-made-it-safe/ • Review is the bottleneck now: How we let AI approve pull requests (safely): https://rewind.com/blog/ai-approve-pull-requests-safely/ *Where to find Claire Vo:* ChatPRD: https://www.chatprd.ai/ Website: https://clairevo.com/ LinkedIn: https://www.linkedin.com/in/clairevo/ X: https://x.com/clairevo _Production and marketing by https://penname.co/._ _For inquiries about sponsoring the podcast, email jordan@penname.co._

Claire Vohost
Aug 5, 202624mWatch on YouTube ↗

CHAPTERS

  1. 0:00 – 2:33

    The hidden PR review backlog created by AI coding

    Claire frames the core problem: AI makes it easy to generate lots of pull requests, but human review capacity doesn’t scale. This creates a growing queue that slows shipping and wastes attention on low-value reviews.

    • AI-generated PR volume is overwhelming many teams
    • Engineering leaders feel the pain most acutely
    • Review queues become the new bottleneck after adopting AI coding
    • Goal: keep shipping velocity without sacrificing safety
  2. 2:33 – 3:04

    Why you don’t need humans to review every AI PR

    She challenges the default assumption that every PR must be reviewed line-by-line by a human. The proposed solution is to put AI in the loop to triage and only require humans where risk is meaningful.

    • The common objection: “we review all human PRs, so we must review all AI PRs”
    • In 2026 workflows, AI can safely reduce mandatory human review
    • Focus human attention on PRs that truly require judgment
    • Use automation to clear low-risk changes faster
  3. 3:04 – 5:05

    Intercom’s approach: AI-approved PRs can be safer (with metrics + compliance)

    Claire cites Intercom’s system for scoring and auto-approving PRs, emphasizing they optimized for quality and safety—not just speed. She also explains how auditability and policy alignment can satisfy SOC 2/HIPAA-style constraints.

    • Intercom increased PR throughput significantly by auto-scoring/approving
    • AI-approved PRs were ~5x faster to approve
    • Lower revert rates for AI-written/AI-approved code
    • Compliance is possible with auditable, defensible policies and logs
  4. 5:05 – 6:05

    Technical inspiration: Diff Vader/Rewind-style risk scoring signals

    She references another implementation that breaks risk into concrete signals like blast radius and CI status. These references help shape the components of her own agent design.

    • Risk signals can include blast radius, correctness, and workflow checks
    • CI/actions status is part of determining readiness and safety
    • Real-world writeups provide a blueprint for building your own
    • Motivation: remove “boring” low-risk PRs from the queue
  5. 6:05 – 9:08

    Why Vercel Eve: a practical framework for enterprise Slack + GitHub agents

    Claire introduces Vercel Eve and explains why it’s her default choice for deploying internal agents. Eve’s directory-based structure, multi-channel support, sandboxing, and managed connectors reduce setup friction.

    • Eve agents are organized as a directory of instructions, skills, and code
    • Built-in channel support makes Slack/GitHub interaction easier
    • Sandbox execution helps for tasks like checking out repos and inspecting diffs
    • Vercel Connectors simplify OAuth/refresh tokens and enterprise integrations
  6. 9:08 – 10:08

    The Codex prompt that kicked off the entire bot build

    She shows how minimal the initial Codex prompt was—just a clear objective to review PRs after checks pass, classify risk, and auto-approve low-risk changes. From there, she steered Codex to implement it as an Eve agent.

    • Simple starting prompt: review after checks are green, score risk, auto-approve low-risk
    • Light steering to choose Eve as the implementation framework
    • Few iterations were needed to get to a working repo
    • Emphasis: you don’t need a huge spec to begin
  7. 10:08 – 11:39

    Setup shortcut: using Codex browser automation for GitHub/Slack configuration

    Claire highlights that the hardest part is often SaaS setup—permissions, manifests, and app configuration—not code. Her “meta tip” is to use browser automation to click through setup flows while she verifies and handles 2FA.

    • GitHub app + Slack bot setup is permission-heavy and tedious
    • Codex “Chrome browser use” can navigate configuration screens
    • Human stays in the loop for verification and 2FA
    • Great for any complex third-party tool configuration
  8. 11:39 – 12:10

    What the agent does end-to-end: read diff, score risk, approve or escalate

    She outlines the core workflow: the agent reads the PR and diff, produces a risk score with evidence, approves low-risk PRs, escalates to humans when needed, and requests changes for blockers. This mirrors a human review process while scaling throughput.

    • Reads PR content + exact diff
    • Scores risk and publishes rationale/evidence
    • Low risk: approve; medium/high: escalate to human
    • Blockers trigger a “request changes” style outcome
  9. 12:10 – 13:11

    How it works technically: GitHub events → Eve channel → sandbox checkout → output

    Claire explains the integration flow: a GitHub App triggers on PR readiness, Vercel routes the event to the GitHub channel, then Eve spins up a sandbox to inspect code and run skills/tools. Results include review output plus Slack notifications for the team.

    • GitHub App triggers after PR is ready (post-checks)
    • Vercel GitHub integration forwards events into Eve’s GitHub channel
    • Sandbox checks out repo, inspects diff, runs evaluation skills/tools
    • Outputs approval/status + comment; then notifies Slack
  10. 13:11 – 14:11

    Inside an Eve agent: channels, instructions, skills, and minimal files

    She breaks down what’s in the agent repo: a GitHub channel, concise instruction text, a PR review skill, tools for reading PR context and making decisions, plus a Slack notifier. The key message is that the implementation can be surprisingly small and maintainable.

    • Core pieces: GitHub channel + instructions + review skill + tools + Slack notifier
    • Instructions are short (a few paragraphs/bullets) but effective
    • Most logic can live in markdown/text plus TypeScript where needed
    • Eve’s structure encourages simplicity over over-engineering
  11. 14:11 – 15:42

    Trigger rules and permissions: reduce noise and only run when it matters

    Claire notes the importance of configuring when the bot runs so it doesn’t spam early or on incomplete PRs. Permissions are scoped to PR contents, checks, metadata, and the ability to comment/approve as appropriate.

    • Avoid triggering on every PR update before checks finish
    • Scope GitHub permissions to PRs, file contents, CI/actions, metadata
    • Use rules to ensure the bot runs at the right lifecycle stage
    • Automation handles setup, but teams should verify access boundaries
  12. 15:42 – 17:13

    Six-component risk scoring model and thresholds (low/medium/high)

    She explains the risk rubric: blast radius/change surface, reversibility, security/data impact, operational impact, and verification gaps (tests/CI completeness), among others. A numeric score maps to low/medium/high bands that determine whether humans must approve.

    • Risk factors include blast radius, reversibility, security/data concerns, ops impact, and test/CI coverage gaps
    • Repo-specific categories: docs low risk; feature logic medium; auth/billing high
    • Diff size alone does not define risk
    • Thresholds: <24 low; 25–64 medium; 65+ high; medium/high require human approval
  13. 17:13 – 21:46

    Merge Mommy in action: three PR examples (auto-approve, blocked, escalate)

    Claire demos the bot on real PRs: a docs PR scored low but blocked due to merge conflicts, a docs PR that receives an approval signal, and a larger deprecation/refactor PR scored medium and escalated. She also explains why a human still clicks approve due to repo rules.

    • Docs-only PR: low risk but blocked when merge conflicts exist
    • Docs PR: low risk and marked approved by the bot
    • Deprecation/refactor PR: medium risk due to change surface/API behavior; not auto-approved
    • Repo rules may require a human approval even if the bot “approves” (gray check as signal)
  14. 21:46 – 24:13

    Recap: build your own + add evals to keep the agent honest

    She summarizes the build recipe—Eve agent + PR-reading skill + risk score + GitHub/Slack connectors—and reiterates the benefit: faster cycle time with attention focused on risky changes. Finally, she recommends running evals and logging each review so engineers can audit and improve the agent over time.

    • Use Eve, write concise instructions, implement PR read + risk scoring
    • Connect to GitHub for PR context and Slack for escalation/ops flow
    • Result: faster PR cycle time and higher throughput
    • Add evals/logging for continuous improvement and safety validation

Get more out of YouTube videos.

High quality summaries for YouTube videos. Accurate transcripts to search & find moments. Powered by ChatGPT & Claude AI.