Memory for Agents: Personalization Beyond the Context Window
with Aishwarya Srinivasan, Arvind Narayanamurthy
Long-lived agents need continuity, but poor memory creates stale context, privacy risk, and user mistrust. Builders need patterns for what to remember, how to retrieve it, and when to forget so agents become more useful over time without becoming unpredictable or intrusive.
Loading session access
What you will learn
1
Decide what agents should remember
Learn what to store, update, retrieve, and forget in long-lived agent systems.
2
Build personalization users trust
Connect memory retrieval to useful, inspectable, and correctable experiences.
3
Reduce stale or risky context
Avoid privacy, trust, and reliability failures caused by poor memory design.
About this session
Long-lived agents need continuity, but poor memory creates stale context, privacy risk, and user mistrust. Builders need patterns for what to remember, how to retrieve it, and when to forget so agents become more useful over time without becoming unpredictable or intrusive.
Guest speaker
Rudraj Mehta
Product @ Mem0 · Mem0
Rudraj Mehta works on product at Mem0, the memory layer for AI agents. He focuses on memory infrastructure, retrieval, and context portability for agentic applications, helping builders think clearly about what agents should keep and recall.
The Gen Academy
Hosted by Aishwarya Srinivasan and Arvind Narayanamurthy.
Aishwarya Srinivasan
AI Advisor / AI Educator
Aishwarya Srinivasan is the Co-Founder of The Gen Academy and a Developer Relations Lead at Nebius. Her experience spans Fireworks AI, Microsoft for Startups, Google Cloud and IBM, where she worked with developers and businesses on practical AI and machine-learning solutions. She holds a postgraduate degree in Data Science from Columbia University and teaches AI engineering, applied machine learning, generative AI and LLMOps.
Arvind Narayanamurthy
Founder @ The Gen Academy | AI Solutions Architect | Ex - Adobe, Microsoft, IBM
Arvind brings a cross-company perspective on AI at scale, built across Microsoft, IBM, and Adobe, where he led data science teams and developed production-grade machine-learning solutions. He has built and deployed enterprise AI systems and focuses on translating AI concepts into practical, production-ready solutions. He holds a Master's from Carnegie Mellon University.