Databricks Certified Generative AI Engineer Associate
Exam overview, official domain weights and free sample questions. Subscribers get 330 practice questions, 85 flashcards, 11 labs, a study guide and video lessons for this exam.
Level up this campaign
Start with the free sample questions below, or get full access for $4.99/month. One subscription unlocks every live course.
Exam at a glance
- Exam code
- Generative AI Engineer Associate
- Questions
- 45
- Time
- 90 minutes
- Question types
- multiple choice, multiple selection
- Passing score
- not published by vendor
- Exam fee
- USD 200, plus applicable taxes
- Delivery
- online proctored, test center (listed on the certification page)
- Prerequisites
- None required; related training highly recommended. Six months of hands-on Databricks experience with the outline topics recommended
- Renewal
- Valid 2 years; recertify by passing the current live exam
- Version notes
- not published by vendor; Databricks asks candidates to recheck the guide two weeks before the exam
From the official exam page (checked 2026-11-17). Always confirm details with the vendor: official exam page, official objectives.
Domains and weights
- 1.1 Design a prompt that elicits a specifically formatted response
- 1.2 Select model tasks to accomplish a given business requirement
- 1.3 Select chain components for a desired model input and output
- 1.4 Translate business use case goals into a description of the desired inputs and outputs for the AI pipeline
- 1.5 Define and order tools that gather knowledge or take actions for multi-stage reasoning
- 1.6 Determine how and when to use Agent Bricks (Knowledge Assistant, Multiagent Supervisor, Information Extraction) to solve problems
- 2.1 Apply a chunking strategy for a given document structure and model constraints
- 2.2 Filter extraneous content in source documents that degrades quality of a RAG application
- 2.3 Choose the appropriate Python package to extract document content from provided source data and format
- 2.4 Define operations and sequence to write given chunked text into Delta Lake tables in Unity Catalog
- 2.5 Identify needed source documents that provide necessary knowledge and quality for a given RAG application
- 2.6 Use tools and metrics to evaluate retrieval performance
- 2.7 Design retrieval systems using advanced chunking strategies
- 2.8 Explain the role of re-ranking in the information retrieval process
- 3.1 Select Langchain/similar tools for use in a Generative AI application
- 3.2 Qualitatively assess responses to identify common issues such as quality and safety
- 3.3 Select chunking strategy based on model & retrieval evaluation
- 3.4 Augment a prompt with additional context from a user's input based on key fields, terms, and intents
- 3.5 Create a prompt that adjusts an LLM's response from a baseline to a desired output
- 3.6 Implement LLM guardrails to prevent negative outcomes
- 3.7 Select the best LLM based on the attributes of the application to be developed
- 3.8 Select an embedding model context length based on source documents, expected queries, and optimization strategy
- 3.9 Select a model from a model hub or marketplace for a task based on model metadata/model cards
- 3.10 Select the best model for a given task based on common metrics generated in experiments
- 3.11 Utilize MLflow and Agent Framework for developing agentic systems
- 3.12 Compare the evaluation and monitoring phases of the Gen AI application life cycle
- 3.13 Enable multi-agent systems to leverage Genie Spaces or conversational API to retrieve data
- 4.1 Code a chain using a pyfunc model with pre- and post-processing
- 4.2 Control access to resources from model serving endpoints
- 4.3 Code a simple chain according to requirements
- 4.4 Choose the basic elements needed to create a RAG application: model flavor, embedding model, retriever, dependencies, input examples, model signature
- 4.5 Register the model to Unity Catalog using MLflow
- 4.6 Create and query a Vector Search index
- 4.7 Identify how to serve an LLM application that leverages Foundation Model APIs
- 4.8 Explain the key concepts and components of Mosaic AI Vector Search
- 4.9 Identify batch inference workloads and apply ai_query() appropriately
- 4.10 Configure vector search for a particular solution based on number of embeddings, update frequency, latency, and cost requirements
- 4.11 Configure a persistent datastore to store and retrieve intermediate memory or structured information
- 4.12 Apply CI/CD best practices such as updating a Vector Search index, promoting prompts across environments, and testing individual components of an agent
- 4.13 Integrate managed, external, and custom MCP servers based on a given application requirements
- 4.14 Apply prompt version control and manage prompt lifecycle
- 4.15 Develop an appropriate interactive user facing interface for an agent usage scenario (Apps, Slack, Teams, etc.)
- 5.1 Use masking techniques as guard rails to meet a performance objective
- 5.2 Select guardrail techniques to protect against malicious user inputs to a Gen AI application
- 5.3 Use legal/licensing requirements for data sources to avoid legal risk
- 5.4 Recommend an alternative for problematic text mitigation in a data source feeding a GenAI application
- 6.1 Select an LLM choice (size and architecture) based on a set of quantitative evaluation metrics
- 6.2 Select key metrics to monitor for a specific LLM deployment scenario
- 6.3 Evaluate agent performance using MLflow scoring and tracing
- 6.4 Use inference logging to assess deployed RAG application performance
- 6.5 Use Databricks features to control LLM costs
- 6.6 Use inference tables and Agent Monitoring to track a live LLM endpoint
- 6.7 Identify evaluation judges that require ground truth
- 6.8 Use AI Gateway (Inference Tables, Usage Tables, and rate limiting) to track an LLM or agent deployed via Agent Framework
- 6.9 Use Databricks custom Scorers for evaluating agents and LLMs
- 6.10 Incorporate SME feedback to improve agent performance
Free sample questions
Original questions in the style of the exam. Pick an answer to see the explanation.
A downstream job parses LLM output into a table. What prompt design helps most?
Documents are long manuals with headings. Which chunking strategy fits?
A team wants a framework to chain prompts, retrievers and tools in Python. What fits?
Full access to all 45 certifications.
One $4.99/month subscription unlocks every cert, video, lab, flashcard, practice question and study guide. 45 certifications live, growing to 100+, for $4.99/month. Cancel anytime.