Applied AI Governance

Your business needs an AI platform where users get governed answers from live data, knowledge workers search institutional memory, and agents orchestrate complex workflows, all while partners access the same capabilities through their own identity providers.

The tools will change. The principles won't. Govern the invariants.

To build this on Databricks, you will use Genie for natural language analytics, Vector Search for knowledge retrieval, Agent Bricks for multi-agent orchestration, MCP servers for tool governance, Unity Catalog for data access control, and AI Gateway for model traffic management. This site shows you how to govern all of it.

Presentations

Identity & Governance Overview

OBO vs M2M vs Federation, UC governance, scope model. Executive audience.

Identity Patterns

AuthN vs AuthZ, OBO/M2M/Federation flows, decision guide, scopes, SPs.

Federation Deep Dive

Token anatomy, 7 enforcement points, grants checklist.

Federation Blueprint

Step-by-step implementation guide. Auth0, Okta, Entra. Error catalog, smoke test.

UC Governance

Four-layer access control, row filters, column masks, ABAC.

AI Orchestration

Agents, Apps, MCP, AI Gateway, external auth.

AI Gateway Patterns

Databricks vs external gateway vs UC-native controls.
Documentation
Governance Framework Seven pillars, design principles, adaptability model Authentication (AuthN) IdP delegation, unified client auth, cloud differences Authorization (AuthZ) OBO, M2M, Federation, UC model, scopes, SPs Federation Exchange External IdP token exchange, role-based SPs Federation Blueprint 12 prerequisites, 7-step flow, IdP reference, error catalog UC Governance Row filters, column masks, ABAC, Genie patterns Orchestration Architecture Model Serving, MCP, AI Gateway, Lakebase
Databricks Documentation
Unified Client Auth OAuth U2M OAuth M2M Databricks Apps Auth Agent Authentication Unity Catalog ABAC Tutorial Security Overview
GitHub All Presentations Governance Framework