Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Learn how to engineer trustworthy AI agent systems by combining Dataiku's LLM Mesh with Databricks Mosaic AI in this 22-minute conference talk. Discover how to streamline the entire AI agent lifecycle from data ingestion and preparation in the Lakehouse to prompt engineering LLMs hosted on Mosaic AI Model Serving Endpoints. Explore visual orchestration of multi-step chains and real-time monitoring capabilities that ensure both resilience and transparency in AI agent systems. Follow along with a live demonstration of a Dataiku flow that connects to a Databricks hosted model, incorporating automated validation, lineage tracking, and human-in-the-loop review processes before exposing the agent through Dataiku's Agent Connect interface. Gain actionable patterns for implementing guardrails, logging decision processes, and surfacing explanations to enable faster and safer deployment of trustworthy domain-specific agents in your organization. Master the integration of these platforms to automate complex tasks while maintaining intelligent decision-making capabilities with proper oversight and accountability measures.
