Databricks GenAI Engineer Associate cheat sheet

Exam at a glance

Domain weightings

How much of the exam each domain covers. Spend your study time in proportion — the heavier the domain, the more questions you'll see.

Key terms

Retrieval Augmented Generation

Retrieval Augmented Generation (RAG) is a technique that grounds a model's responses in retrieved external data rather than only its training. The GenAI Engineer exam centers on building RAG applications on Databricks.

Databricks Vector Search

Databricks Vector Search is a serverless vector database that indexes embeddings for similarity retrieval in RAG applications. The GenAI Engineer exam covers it for data preparation and retrieval.

Embedding

An embedding is a numeric vector representation of text that captures semantic meaning for similarity search. The GenAI Engineer exam covers generating and storing embeddings for retrieval.

Chunking

Chunking is the process of splitting documents into smaller passages so they can be embedded and retrieved effectively. The GenAI Engineer exam covers chunking strategies in data preparation.

Mosaic AI

Mosaic AI is the Databricks suite for building, serving, and evaluating AI and generative AI applications. The GenAI Engineer exam covers Mosaic AI tools for development, serving, and evaluation.

Foundation Model APIs

Databricks Foundation Model APIs provide access to hosted large language models for inference from within Databricks. The GenAI Engineer exam covers using them and external models in application development.

LangChain

LangChain is an open-source framework for composing LLM calls, tools, and retrievers into chains and agents. The GenAI Engineer exam covers building RAG chains with LangChain on Databricks.

Agent

An agent is a generative AI component that plans and calls tools over multiple steps to complete a task. The GenAI Engineer exam covers decomposing tasks into chains and agents when designing applications.

MLflow

MLflow is an open-source platform, deeply integrated with Databricks, for tracking, logging, and registering models and AI applications. The GenAI Engineer exam covers logging and registering chains with MLflow before deployment.

Model Serving

Databricks Model Serving is a service that deploys models and AI applications behind scalable REST endpoints. The GenAI Engineer exam covers deploying chains with Model Serving in the assembling and deploying domain.

Unity Catalog

Unity Catalog is the Databricks governance layer that manages access, lineage, and permissions for data, models, and AI assets. The GenAI Engineer exam covers it in the governance domain.

Governance guardrails

Governance guardrails are safety filters and policies that constrain generative AI inputs and outputs, such as blocking unsafe content or masking PII. The GenAI Engineer exam covers guardrails in the governance domain.

LLM-as-a-judge

LLM-as-a-judge is an evaluation approach that uses a language model to score the quality of generative AI outputs. The GenAI Engineer exam covers it, with Mosaic AI Agent Evaluation, in the evaluation and monitoring domain.

Inference table

An inference table is a Databricks table that automatically logs the requests and responses of a served model for monitoring. The GenAI Engineer exam covers inference tables for monitoring deployed applications.