Why it matters
It focuses on the data layer under AI products: latency, scale and keeping agents from damaging data. One abstract covers sandboxing agents and cutting database operating costs to free up budget for AI.
The tokenmaxxing angle
Ask how retrieval and real-time data costs compare with model token costs in a production RAG system. Which is the bigger line item, and where does caching or a cheaper database tier help most?
From the organizers
Thu Dec 3, 6:00 PM CT at 25 E Washington St, Chicago Loop. Free, 54 guests registered. Confirmed speakers: Robert Hodges (EnterpriseDB) and Arnaud Adant (Jump Trading). Talks 6:15 to 8:00, then networking.