Back/Engineering/Devin
AdvancedEngineering

Scale Code Quality with an Automated 'Land PR' AI Workflow

Implement a QA loop for AI-generated code using Devin. This playbook combines automated code reviews with an agent-recorded video walkthrough for visual verification, ensuring high-quality merges at scale.

Scale Code Quality with an Automated 'Land PR' AI Workflow

Before you start

Tools used

  • Devin

    AI software engineer by Cognition Labs

Step by step

The workflow

Follow the sequence once, then adapt the prompts, checks, and handoffs to your own setup.

6 steps

Step01

Trigger 'Land PR'

When an agent signals that a pull request (PR) is ready for review, kick off your 'Land PR' playbook.

Step02

Run Automated Review

The playbook first runs Devin Review on the PR. Run this in a loop (up to two times) to allow the agent to find and fix its own bugs.

Step03

Generate Video Walkthrough

The agent records a video of itself testing the new feature in a browser, narrating the test cases with captions and showing a checklist of results.

This is an incredibly powerful form of verification that goes beyond simple unit tests.

Step04

Perform Human Approval

Watch the short video to visually confirm the feature works as expected.

Step05

Issue Merge Command

Give the final approval command to the agent to proceed with the merge.

Example prompt
Video approved. Land it.
Step06

Merge to Main

The agent merges the approved PR into the main branch, completing the workflow.

Build your next product with ChatPRD

Turn an idea into a PRD, user stories, and a plan.

Try ChatPRD free

Start shipping
better products.

Join 100,000+ product managers who use ChatPRD to write better docs, align teams faster, and build products users love.

Free to start
No credit card
SOC 2 certified
Enterprise ready