[State of Context Engineering] Agentic RAG, Context Rot, MCP, Subagents — Nina Lopatina, Contextual

The podcast explores the current state and future directions of context engineering, featuring Nina Lopatina from Contextual AI. The discussion covers the shift from traditional RAG to agentic RAG, highlighting the benefits of query reformulation and the use of sub-agents for specific tasks. Lopatina and the host examine the challenges and opportunities in scaling context engineering, including managing context rot and optimizing system prompts. They also touch on the importance of industry benchmarks for evaluating performance at scale, using the Retail Universe hackathon dataset as an example. The conversation further addresses the role of MCP servers and registries, and the potential of JEPA for optimizing system prompts.