Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
This talk by Alessandro Pireno, Solutions Director at SurrealDB, explores how knowledge graphs and semantic search can enhance LLM capabilities in production environments. Learn how to implement AI "agents" powered by large language models while addressing critical MLOps challenges including unpredictable decision paths, hallucinations, and debugging difficulties. Discover a structured approach to maintaining reliability in agent-based workflows through clear task boundaries, effective guardrails, and comprehensive decision tracing. The presentation shares valuable lessons from implementing agent-based workflows at scale and demonstrates how an open-source framework built on Prefect can help orchestrate and monitor these complex systems. By the end of this 29-minute session from MLOps World, you'll understand how to transform opaque AI agents into transparent, trustworthy components of your machine learning operations, effectively harnessing their power without sacrificing control over your pipelines.
