Description
Welcome to the Agentic AI Explained series. This is video 3 of 10, covering the key building blocks behind modern AI agent systems. This video covers Databricks Unity AI Gateway, a centralized governance layer for the runtime interactions between models, agents, MCP servers, and tools. It gives developers flexibility to use different AI models and services while giving platform teams one place to control access, traffic, cost, and behavior. 🔗 Learn more about Unity AI Gateway: https://docs.databricks.com/aws/en/ai-gateway/ 🔗 GitHub repo for this series: https://github.com/viktoriasemaan/agentic-ai-explained-labs The video covers 4 key areas: ▪️ Access and routing: control which models and AI services teams can use, and route requests across different model providers and destinations. ▪️ Cost controls: apply rate limits, track usage, set budgets, and enforce spend thresholds and hard caps. ▪️ Policies and guardrails: apply service policies to requests and responses based on who is calling and what the interaction contains. ▪️ Monitoring and auditing: track requests, token usage, latency, and cost, while logging requests and responses for monitoring and debugging. The resul…
Description from YouTube. Full content on the video page.
More from Databricks
NewsHow HSS Offloads Provider Administrative Burden with the Databricks Data + AI Platform
NewsHow NOL Universe Scales Global Travel Operations for 1,000+ Users With Databricks
NewsHow adidas Uses Databricks to Build Better Products
Adidas uses Databricks' lakehouse platform to centralize all its data—from product to football-related insights—enabling faster analytics across the organization. The company's Genie analytics tool helps analysts spend less time processing data and more time on strategic questions, ultimately supporting better product development.
NewsDatabricks for Good x MapAid: Creating a Searchable Database for Groundwater Discovery
MapAid is using Databricks to build an AI groundwater mapping system called Well Mapper that processes water documents to identify accurate well-drilling locations in Ethiopia, improving on the current 30% success rate. The system analyzes 400 well logs in half a second instead of four weeks, with potential to double Ethiopia's food supply through improved irrigation.
NewsHow Databricks Genie Automates Data Workflows with Genie Ontology and Scheduled Tasks
Databricks Genie enables ontology by default for business context and adds document/PDF uploads, direct Unity Catalog queries, and team collaboration features in chat. Scheduled tasks automate recurring workflows with embedded visualizations and PDF outputs accessible across web, desktop, and mobile platforms.