Getting GenAI to Production with Mosaic AI Gateway in Databricks
Summary
The video demonstrates how to productionize GenAI applications using Databricks' Mosaic AI Gateway, highlighting features like usage tracking, inference tables, AI guardrails, rate limits, and model fallbacks. It shows how to configure these features through the Databricks UI and monitor application performance and costs using built-in dashboards.
Summary generated by brickster.ai from the video transcript.
More from Advancing Analytics
NewsThe Shift to System One | System One Models - Part One
The video introduces system one AI models designed for fast, low-cost classification and decision-making instead of token-by-token text generation. It demonstrates how these models provide reliable probability confidence scores and fixed-option routing for workflows like query categorization and real-time automation.
NewsBig Data LDN 2026 - Lakebase & LTAP | Simon Whiteley & Holly Smith
Lakebase and LTAP enable two separate engines to read from a single copy of data by making PostgreSQL page servers and safekeepers behave like Delta or Iceberg tables. This architecture eliminates the need for manual synchronization between operational and analytical systems to support real-time AI agents and applications.
NewsBig Data LDN 2026 - what's the vibe like? | Simon Whiteley & Holly Smith
The Big Data London 2026 conference shows a shift from AI hype and fearmongering toward practical business value and meaningful implementation. Practitioners are focusing on proven tools and realistic use cases rather than building expensive custom models from scratch.
NewsRethinking Data Strategy for the Genie Ontology World
The video teaches data teams how to rethink traditional data strategy for runtime AI tools like Databricks Genie Ontology by categorizing enterprise data into a multi-tiered maturity model rather than forcing everything into a single curated semantic layer. It demonstrates how to establish different governance and maintenance approaches across a structured data estate, ranging from heavily curated walled gardens to managed parks and wider unstructured woodlands.
EventsThe Ontological Definition of Databricks Genie Ontology via OntoRank
Databricks Genie Ontology uses a ranking algorithm (OntoRank) to dynamically infer data definitions based on source credibility, usage frequency, and certification, enabling AI agents to answer questions without requiring formal ontologies. The tool democratizes data access but risks surfacing incorrect definitions if not paired with basic data governance practices.
NewsAI Watermarking, Databricks AI Extract, Hugging Face, and Unity Catalog | AI Newsround - Summer 2026
Claude and other AI models will invisibly watermark generated text to ensure content traceability, while Databricks AI Extract achieves 94.7% accuracy on complex documents and extracts charts as structured data. Databricks added skills to Unity Catalog as governed assets and launched AI Gateway to centralize access to multiple AI models, enabling rapid evaluation and swapping without code changes.