1017: Vector Search, Agentic Memory and Effective RAG, with MongoDB’s Pete Johnson

Four out of every five organizations have AI steering committees and success metrics, which should set them up for AI success, and yet only one in five sees any return on AI investment. Today's guest is the exceptional Pete Johnson, field CTO of AI at MongoDB, where he spent the year so far on a world tour advising over 100 companies on their AI strategies, all backed by more than 30 years of experience at enterprise

It goes beyond the title with direct discussion of like, data, know, including: My guest today explains what these AI ROI winners are doing differently.

1. 01In this episode, Pete reveals which AI deployments are actually generating ROI, why the embedding model you choose can make or break your RAG pipeline, and how token maxing became
2. 02collectively as an industry, we've spent all this CapEx developing the models
3. 03And it was the first time I heard a customer talk about that they had agents deployed in production and they were getting ROI out of them