How to Improve AI Apps with Automated Evals

How to Improve AI Apps with Automated Evals

Shaw Talebi via YouTube Direct link

2 Types of Automated Evals - 4:25

5 of 14

5 of 14

2 Types of Automated Evals - 4:25

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

How to Improve AI Apps with Automated Evals

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Introduction - 0:00
  2. 2 The Typical LLM Workflow - 0:21
  3. 3 The Problem - 1:11
  4. 4 Automed Evals - 1:50
  5. 5 2 Types of Automated Evals - 4:25
  6. 6 Example: Eval-driven LinkedIn Ghostwriter - 7:03
  7. 7 Step 1: Identify Failure Modes - 9:36
  8. 8 Step 2: Create LLM Judge - 10:49
  9. 9 Step 3: Curate User Inputs - 19:49
  10. 10 Step 4: Generate LI Posts - 20:30
  11. 11 Step 5: Apply Evals - 21:12
  12. 12 Step 6: Review Results and Refine - 22:06
  13. 13 The Results - 25:19
  14. 14 Demo - 26:59

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.