Watch more from .local London '26 → https://youtu.be/GIhtQaxhwAc As AI systems evolve from simple prompt–response models to autonomous, goal‑driven agents, memory becomes a first‑class design concern. This talk explores how agents leverage context, short‑term and long‑term memory, and modern memory engineering patterns to reason, learn, and behave consistently over time. It also covers practical architectures and real‑world example of building reliable, stateful AI agents.   00:00:00 - Introduction & The MongoDB + LangChain Partnership 00:02:12 - The Lost Context Problem in AI Applications 00:03:49 - Evolution of AI: From RAG to Agentic AI 00:04:58 - Prompt, Context, and Memory Engineering Explained 00:06:28 - Deep Dive: Tool Calling & RAG Patterns 00:09:11 - What is an AI Agent? Core Capabilities 00:10:01 - The Need for Persistent Memory Architecture 00:12:00 - Human vs. LLM Memory (Parametric vs. Working) 00:13:42 - Short-Term Memory vs. Long-Term Memory Patterns 00:16:47 - Coordination Memory for Multi-Agent Systems 00:17:39 - Data-to-Memory Transformation Flow 00:20:03 - Building Agents with LangGraph Primitives 00:21:24 - Human-in-the-Loop & Stateful Execution 00:23:40 - LangGraph Nodes, Edges, and State 00:25:11 - Full Stack View: MongoDB Server & Store Implementation 00:28:05 - Demo: Context-Aware AI Application in Action 00:29:41 - Key Takeaways & Conclusion Subscribe to the MongoDB for Developers YouTube Channel: https://www.youtube.com/@MongoDBDevelopers?sub_confirmation=1 Sign-up for a free cluster → https://www.mongodb.com/cloud/atlas/register Subscribe to MongoDB YouTube→ https://mdb.link/subscribe Visit Mongodb.com → https://mdb.link/MongoDB Read the MongoDB Blog → https://mdb.link/Blog Read the Developer Blog → https://mdb.link/developerblog MongoDB for Developers YouTube Channel → https://www.youtube.com/@MongoDBDevelopers

 204      10