Free Lesson
Optimize Your Dev Setup For Evals w/ Cursor Rules & MCP
Part of The AI Evaluation Handbook
30 min
Jul 15, 2025 1:00 PM
Virtual (Zoom)
In this video
What you'll learn
How to use MCP context for AI evaluation frameworks
Configure MCPs to pull llms.txt intelligently or data from your eval system to automate data analysis and debugging.
Cursor rules for Phoenix, Braintrust, and Inspect
Customize your dev environment for the specific tool you are using and your preferences. Isaac will share his recipes.
Use AI for evaluation development and debugging
Greatly reduce the friction of setting up evals by automating away the tedious bits.
Why this topic matters
AI evaluations are complex and model context is what lets AI help you. We will cover different approaches an strategies for giving coding models context to help you, and show the most robust way to curate that information. In you see and learn my process for creating cursor rules for common AI evaluation tools such as Phoenix, Braintrust, and Inspect that will make you significantly faster at bui
You'll learn from

Isaac Flath
AI Engineer & Fullstack Developer

Hamel Husain
ML Engineer with 20 years of experience

Shreya Shankar
ML Systems Researcher Making AI Evaluation Work in Practice
.png&w=1536&q=75)