Databricks platform components for AI applications

An AI application often touches several layers: governed source data, transformations and feature preparation, model or foundation-model access, orchestration, evaluation, and a serving interface. Databricks integrates data and AI workflows, but a component should be selected for a concrete responsibility rather than because it is available. Keep development, evaluation, and production settings distinguishable and reproducible. Unity Catalog provides a governance layer for data and AI assets, while model-serving capabilities expose supported models through managed endpoints. MLflow supports experiment tracking and GenAI observability workflows. Product features and names evolve, so verify current workspace availability, region support, permissions, and documentation before building a dependency on a particular service. Think in terms of ownership boundaries. Data owners govern source tables and documents; application code controls retrieval filters and business rules; model endpoints perform inference; evaluation and tracing provide evidence about quality and behavior. Unity Catalog can help govern supported data and AI assets, while MLflow can organize experiments and GenAI traces. These services do not remove the need to define workspace permissions or application-level authorization. A useful architecture review asks who owns each asset, which identity accesses it, how it is versioned, and how an operator diagnoses a failure. Implementation drill: trace one representative request through the stages in the diagram. Write down what enters each stage, what output or evidence it produces, and which identity is allowed to perform it. Then test an empty input, an unauthorized request, a dependency timeout, and an unexpected result. For each case, state whether the application should retry, reject, abstain, or ask a person for help. Keep the observed failure as a regression example so changes to prompts, models, data, or code can be checked against the same behavior. Practice task: Which service is primarily associated with governance of data and AI assets?