New York

October 15–17, 2025

Berlin

November 3–4, 2025

London

June 2–3, 2026

How Tilt’s Review Bot transformed its code reviews

Using observability tools to code with your eyes open.

Hosted by James Garrett

October 08, 2025

On demand video

Login or join LeadDev.com to view this content

Create an account to access our free engineering leadership content, free online events and to receive our weekly email newsletter. We will also keep you up to date with LeadDev events.

Register with google

We have linked your account and just need a few more details to complete your registration:

Terms and conditions

 

 

Enter your email address to reset your password.

 

A link has been emailed to you - check your inbox.



Don't have an account? Click here to register

James and his team at Tilt were struggling with inconsistent code reviews that slowed down development velocity. Their previous tool was overly noisy, commenting on every PR regardless of risk level, and provided corrections without explaining the “why” behind feedback.

By systematically documenting their engineering knowledge, staff engineers created detailed guidelines covering everything from background tasks to error handling. By integrating Augment with their Notion MCP for core concepts and Linear MCP for QA notes, Tilt built a comprehensive knowledge base alongside a rigorous testing process requiring before/after PR comparisons for any rule changes.

What you’ll learn:

  • How Tilt improved first-time PR approval rates
  • How to build a knowledge base using AI
  • Testing strategies for AI development

Promoted Partner Content