Why it matters
This is a hands-on production RAG workshop, not a demo — it explicitly covers cost management and latency optimization alongside retrieval accuracy, the exact tradeoff builders must master to keep RAG pipelines from burning token budgets.
The tokenmaxxing angle
The curriculum names cost management and performance-drift detection as core production concerns — a reminder that retrieval quality and token spend trade off directly: sloppy chunking and over-fetched context are silent multipliers on your inference bill.
From the organizers
Meetup page lists hosts Justin G. (Super Organizer) and Thibaud of the AppliedAI group; workshop runs 12:30-5pm CDT at OWS-150, Owens Science Hall, University of St. Thomas, 2115 Summit Ave, Saint Paul; includes a certificate of completion.