E193 - Agentic Memory And The Art Of Forgetting - Stefan Wendin

In Episode 193 of the AIAW Podcast, we welcome back Stefan Wendin, now Deployment Strategist at QuTwo, to explore one of the biggest challenges in building reliable autonomous AI agents: memory management. We discuss how AI agents remember, forget, update, and reconcile conflicting information, and why persistent memory is becoming essential for enterprise AI systems. From knowledge graphs versus vector databases to the transition from MLOps to AgentOps, we examine the engineering challenges of building stateful, trustworthy AI agents that can manage uncertainty and learn from past experiences. We also explore AI governance, Europe's growing investment in sovereign AI infrastructure and AI factories, and the broader implications of artificial memory for human-AI collaboration, decision-making, and the future of AGI.

Follow us on youtube: https://www.youtube.com/@aiawpodcast