Why Study with PlanetCert?
The Latest Questions
Practice questions and exam topics aligned with the current exam objectives.
Detailed Explanations
Go beyond the answer. Master the material with comprehensive learning and professional explanations for every concept.
AI-Powered Insights
Personalized preparation guidance that adapts to your performance and identifies weak spots automatically.
Exam Information
Official specifications published by Databricks
Exam Format
90 min
45
70%
Associate
Registration
$200 USD
Kryterion or online proctoring
English, Japanese, Portuguese BR, Korean
Validity
2 years
Take the current version of the exam; No continuing education credits option available
GEN-AI-ENG Exam Topics and Domains
GEN-AI-ENG is organized into 6 weighted domains. Expect to work with MLflow, LangChain, Unity Catalog, Model Serving, and more.
1
Design Applications
14%
Prompt Engineering and Design
Design a prompt that elicits a specifically formatted response
- Design a prompt that elicits a specifically formatted response
- Select model tasks to accomplish a given business requirement
Model Task Selection
Select model tasks to accomplish business requirements
- Select chain components for desired model input and output
- Translate business use case goals into AI pipeline specifications
Multi-stage Reasoning
Define and order tools for multi-stage reasoning
Define and order tools that gather knowledge or take actions for multi-stage reasoning
2
Data Preparation
14%
Document Chunking Strategies
Apply chunking strategy for document structure and model constraintsAdvanced chunking strategies
- Apply a chunking strategy for a given document structure and model constraints
- Design retrieval systems using advanced chunking strategies
Document Processing
Filter extraneous content in source documentsExtract document content from various formats
- Choose the appropriate Python package to extract document content
- Filter extraneous content that degrades RAG application quality
Data Storage and Retrieval
Write chunked data to Delta Lake with Unity CatalogRe-ranking in information retrieval
- Define operations and sequence to write chunked text into Delta Lake tables
- Explain the role of re-ranking in the information retrieval process
Source Document Selection
Identify needed source documents for RAG applications
- Identify needed source documents that provide necessary knowledge and quality
- Identify prompt/response pairs that align with a given model task
Retrieval Evaluation
Use tools and metrics to evaluate retrieval performance
Use tools and metrics to evaluate retrieval performance
3
Application Development
30%
Tool Creation and Selection
Create tools for data retrieval needsSelect LangChain tools for GenAI applications
- Create tools needed to extract data for given retrieval needs
- Select Langchain/similar tools for use in Generative AI applications
Prompt Engineering and Optimization
Identify how prompt formats change model outputsAugment prompts with additional contextCreate prompts that adjust LLM responsesWrite metaprompts for safety and security
- Augment a prompt with additional context from user input
- Create prompts that adjust LLM responses from baseline to desired output
- Write metaprompts that minimize hallucinations or leaking private data
Quality and Safety
Qualitatively assess responses for issuesImplement LLM guardrails
- Qualitatively assess responses to identify common issues
- Implement LLM guardrails to prevent negative outcomes
Model Selection and Evaluation
Select chunking strategy based on evaluationSelect best LLM based on application attributesSelect embedding model based on requirementsSelect model from marketplace based on metadata
- Select best LLM based on application attributes
- Select embedding model context length based on requirements
- Select model from hub/marketplace based on metadata/model cards
Agent Development
Build agent prompt templates with functionsUtilize Agent Framework for agentic systems
- Build agent prompt templates exposing available functions
- Utilize Agent Framework for developing agentic systems
4
Assembling and Deploying Applications
22%
Chain Development
Code a chain using pyfunc modelCode simple chains according to requirementsCode simple chains using LangChain
- Code a chain using a pyfunc model with pre- and post-processing
- Code a simple chain according to requirements
- Code a simple chain using langchain
RAG Application Assembly
Choose basic elements for RAG applicationsRegister models to Unity Catalog
- Choose basic elements needed to create a RAG application
- Register the model to Unity Catalog using MLflow
Model Deployment
Control access to model serving endpointsSequence steps to deploy RAG endpointsServe LLM applications with Foundation Model APIs
- Control access to resources from model serving endpoints
- Sequence the steps needed to deploy an endpoint for basic RAG application
- Identify how to serve an LLM application that leverages Foundation Model APIs
Vector Search Implementation
Create and query Vector Search indexesKey concepts of Mosaic AI Vector Search
- Create and query a Vector Search index
- Explain the key concepts and components of Mosaic AI Vector Search
Batch Inference
Identify batch inference workloads
- Identify batch inference workloads and apply ai_query() appropriately
- Identify resources needed to serve features for a RAG application
5
Governance
8%
Security and Guardrails
Use masking techniques as guardrailsSelect guardrail techniques for malicious inputs
- Use masking techniques as guard rails to meet performance objectives
- Select guardrail techniques to protect against malicious user inputs
Content Mitigation
Recommend alternatives for problematic text
Recommend an alternative for problematic text mitigation in data sources
Legal and Licensing
Use legal requirements to avoid risk
Use legal/licensing requirements for data sources to avoid legal risk
6
Evaluation and Monitoring
12%
Model Selection and Evaluation
Select LLM based on quantitative metricsSelect key metrics for deployment scenarios
- Select an LLM choice based on quantitative evaluation metrics
- Select key metrics to monitor for specific LLM deployment scenarios
RAG Application Evaluation
Evaluate model performance using MLflowIdentify evaluation judges requiring ground truth
- Evaluate model performance in a RAG application using MLflow
- Identify evaluation judges that require ground truth
Monitoring and Logging
Use inference logging for performance assessmentUse inference tables and Agent Monitoring
- Use inference logging to assess deployed RAG application performance
- Use inference tables and Agent Monitoring to track live LLM endpoints
Cost Management
Control LLM costs for RAG applications
Use Databricks features to control LLM costs for RAG applications
Lifecycle Management
Compare evaluation and monitoring phases
Compare the evaluation and monitoring phases of the Gen AI application life cycle
How do I earn this certification?
Passing GEN-AI-ENG earns the Databricks Certified Generative AI Engineer Associate certification. It sits in the Generative AI track.
Current Level Exams
Next Level Options
- databricks-certified-data-engineer-professional - Databricks Certified Data Engineer Professional
- databricks-certified-machine-learning-professional - Databricks Certified Machine Learning Professional
Alternative Paths
- databricks-certified-data-engineer-associate - Data Engineer AssociateFoundation in data engineering for AI applications
- databricks-certified-machine-learning-professional - Machine Learning ProfessionalAdvanced ML skills complement GenAI expertise
- databricks-certified-data-analyst-associate - Data Analyst AssociateSQL and analytics skills for data preparation
Practice with Precision
The PlanetCert Simulator mirrors the real exam environment with authentic questions and timed pressure.
How to study for this exam?
The most effective way to prepare for GEN-AI-ENG is by using the PlanetCert Simulator to practice questions and review detailed explanations.
What's changed on this exam?
Current Status
- ACTIVE
- Last content update: 2025-04-18
- Announcement date: 2024-05-24
Updates
- MLflow 3.0 Major update - expect new questions on agent observability and prompt registry • Release date: 2025-06-12
- Vector Search 2.0 Performance improvements and new SQL filtering likely in exam • Release date: 2025-06-12
- Agent Bricks 1.0 New tool - may appear in future exam updates • Release date: 2025-06-12
- Unity Catalog Latest Enhanced interoperability and Iceberg support • Release date: 2025-06-12
Who should take this exam?
This exam is typically taken by Data Engineers and Machine Learning Engineers.
- 6+ months of hands-on experience performing generative AI solutions tasks
- Working knowledge of Python and its libraries for RAG application development
- Knowledge of current LLMs and their capabilities
- Knowledge of prompt engineering and evaluation
- Familiarity with LangChain, Hugging Face Transformers
- Experience with Databricks platform