Completed
12:28 - Pattern 2: Plan-Then-Execute
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Design Patterns for Securing LLM Agents Against Prompt Injection - Paper Review
Automatically move to the next video in the Classroom when playback concludes
- 1 00:00 - Introduction
- 2 03:14 - Problem Space
- 3 05:27 - Prompt Injection Defences
- 4 08:11 - The Problem with Prompt Injection Defences
- 5 09:03 - Core Principle
- 6 09:48 - Pattern 1: Agent Selector
- 7 12:28 - Pattern 2: Plan-Then-Execute
- 8 15:03 - Pattern 3: LLM Map-Reduce
- 9 17:05 - Pattern 4: Dual LLM
- 10 20:27 - Pattern 5: Code-Then-Execute
- 11 24:40 - Pattern 6: Context Minimization
- 12 26:22 - Case Studies
- 13 27:08 - Best Practices for Securing LLM Agents
- 14 31:37 - Engineering Considerations
- 15 32:27 - Summary
