This event requires an RSVP; to attend, submit form hereAs AI agents move beyond chat experiences into production systems, memory becomes essential for maintaining context, coordinating long-running workflows, and delivering reliable outcomes over time. The challenge is deciding what information to remember, where to store it, and what to retrieve at runtime. In this workshop, you'll learn a practical framework for architecting memory systems that actually work in production. We'll cover:
Types of memory in agentic systems
Storage patterns: Where to persist memories and how to structure them for retrieval
Retrieval strategies: Combining vector search with metadata, recency, and other signals
Memory lifecycle: When to create, update, or prune memories to keep your system performant
You'll apply this framework by building memory into an AI agent and seeing how different design choices impact behavior.
You will be provided with all the resources required to successfully execute the hands-on portions of the workshop, including Jupyter Notebook templates with pseudocode. During the workshop, you will replace the pseudocode in the templates with your code.
After the workshop, you will also be able to check your learning and earn a skill badge to share with your network!
