Learn to build to better AI Agents through better Context

Dear John,

The longer an agent works, the more repeated, contradictory, or stale information builds up in its context. Models perform worse as their context grows, a problem Jeff Huber and his team at Chroma named Context Rot.

In our new course, Context Engineering, you'll build agent harnesses from scratch in Python and learn to give agents the right information, in the right format, at the right time. Built in partnership with Chroma and taught by Jeff Huber, with guest speaker Drew Breunig.

In this course, you'll learn how to:

• Recognize how an agent’s context fails, and read traces from its harness to spot these failures in your own agents
• Give an agent the right information by guiding its search and tool choices
• Keep an agent’s context in the right format with pruning, compaction, and scratchpads
• Equip an agent with memories it reuses at the right time and updates across sessions as information changes

Learn about Context Engineering and other skills in person at AI Dev NYC. Tickets on sale now.

Keep learning,

The DeepLearning.AI team

Copyright © 2026 deeplearning.ai, All rights reserved.
You are receiving this because you opted in to receive emails from deeplearning.ai.