💻 Beyond Static Benchmarks: Trustworthy evaluation of agentic retrieval on evolving data
How do you know your AI system is actually good when there's no ground truth to compare against? This talk explores evaluating systems that generate open-ended answers over messy, unstructured data, drawing from building evaluation frameworks for RAG agents over financial datasets.
Session Speaker
Tayyibah Khanam Machine Learning Engineer Kensho Technologies Speaker
Login to save this session to your favorites and reserve your seat.