Context Engineering SF: Context Engineering for Engineers - Jeff Huber

In this talk, Jeff Huber, founder of Chroma, introduces the idea of context engineering as a clearer and more practical framework than prompt engineering or RAG. He shares insights from Chroma’s recent research on context limits, showing why curating and optimizing context is essential for building reliable AI systems.

The talk covers how context engineering improves performance by focusing on gathering, filtering, and compacting information, why long context models fall short, and how these ideas apply to agents and multi-step workflows.

Chapters:
00:00 - Introduction to Context Engineering
00:26 - Understanding AI Systems as Programs
01:29 - The Concept of Context Engineering
02:02 - Building Reliable Software with AI
02:31 - Challenges with Long Contexts
03:07 - Chroma's Technical Report Insights
03:57 - Needle in a Haystack Problem
05:08 - The Importance of Context in AI Tasks
06:05 - Gather and Glean Model
06:44 - Data Gathering Techniques
07:31 - Gleaning and Optimizing Data
08:26 - Content Engineering for Agents
09:35 - Challenges with Agent Performance
10:13 - The Role of Compaction
10:57 - Conclusion and Final Thoughts

Видео Context Engineering SF: Context Engineering for Engineers - Jeff Huber канала Chroma