Free Practice Questions for Databricks Certified Generative AI Engineer Associate Certification

Subdomain 1.1: Design a prompt that elicits a specifically formatted response

Subdomain 1.2: Select model tasks to accomplish a given business requirement

Subdomain 1.3: Select chain components for a desired model input and output

Subdomain 1.4: Translate business use case goals into a description of the desired inputs and outputs for the AI pipeline

Subdomain 1.5: Define and order tools that gather knowledge or take actions for multi-stage reasoning

Subdomain 1.6: Determine how and when to use Agent Bricks (Knowledge Assistant, Multiagent Supervisor, Information Extraction) to solve problems

Subdomain 2.1: Apply a chunking strategy for a given document structure and model constraints

Subdomain 2.2: Filter extraneous content in source documents that degrades quality of a RAG application

Subdomain 2.3: Choose the appropriate Python package to extract document content from provided source data and format

Subdomain 2.4: Define operations and sequence to write given chunked text into Delta Lake tables in Unity Catalog

Subdomain 2.5: Identify needed source documents that provide necessary knowledge and quality for a given RAG application

Subdomain 2.6: Use tools and metrics to evaluate retrieval performance

Subdomain 2.7: Design retrieval systems using advanced chunking strategies

Subdomain 2.8: Explain the role of re-ranking in the information retrieval process

Subdomain 3.1: Select Langchain/similar tools for use in a Generative AI application

Subdomain 3.2: Qualitatively assess responses to identify common issues such as quality and safety

Subdomain 3.3: Select chunking strategy based on model & retrieval evaluation

Subdomain 3.4: Augment a prompt with additional context from a user's input based on key fields, terms, and intents

Subdomain 3.5: Create a prompt that adjusts an LLM's response from a baseline to a desired output

Subdomain 3.6: Implement LLM guardrails to prevent negative outcomes

Subdomain 3.7: Select the best LLM based on the attributes of the application to be developed

Subdomain 3.8: Select an embedding model context length based on source documents, expected queries, and optimization strategy

Subdomain 3.9: Select a model from a model hub or marketplace for a task based on model metadata/model cards

Subdomain 3.10: Select the best model for a given task based on common metrics generated in experiments

Subdomain 3.11: Utilize MLflow and Agent Framework for developing agentic systems

Subdomain 3.12: Compare the evaluation and monitoring phases of the Gen AI application life cycle

Subdomain 3.13: Enable multi-agent systems to leverage Genie Spaces or conversational API to retrieve data

Subdomain 4.1: Code a chain using a pyfunc model with pre- and post-processing

Subdomain 4.2: Control access to resources from model serving endpoints

Subdomain 4.3: Code a simple chain according to requirements

Subdomain 4.4: Choose the basic elements needed to create a RAG application: model flavor, embedding model, retriever, dependencies, input examples, model signature

Subdomain 4.5: Register the model to Unity Catalog using MLflow

Subdomain 4.6: Create and query a Vector Search index

Subdomain 4.7: Identify how to serve an LLM application that leverages Foundation Model APIs

Subdomain 4.8: Explain the key concepts and components of Mosaic AI Vector Search

Subdomain 4.9: Identify batch inference workloads and apply ai_query() appropriately

Subdomain 4.10: Configure vector search for a particular solution based on number of embeddings, update frequency, latency, and cost requirements

Subdomain 4.11: Configure a persistent datastore to store and retrieve intermediate memory or structured information

Subdomain 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

Subdomain 4.13: Integrate managed, external, and custom MCP servers based on a given application requirements

Subdomain 4.14: Apply prompt version control and manage prompt lifecycle

Subdomain 4.15: Develop an appropriate interactive user facing interface for an agent usage scenario (Apps, Slack, Teams, etc.)

Subdomain 5.1: Use masking techniques as guard rails to meet a performance objective

Subdomain 5.2: Select guardrail techniques to protect against malicious user inputs to a Gen AI application

Subdomain 5.3: Use legal/licensing requirements for data sources to avoid legal risk

Subdomain 5.4: Recommend an alternative for problematic text mitigation in a data source feeding a GenAI application

Subdomain 6.1: Select an LLM choice (size and architecture) based on a set of quantitative evaluation metrics

Subdomain 6.2: Select key metrics to monitor for a specific LLM deployment scenario

Subdomain 6.3: Evaluate agent performance using MLflow scoring and tracing

Subdomain 6.4: Use inference logging to assess deployed RAG application performance

Subdomain 6.5: Use Databricks features to control LLM costs

Subdomain 6.6: Use inference tables and Agent Monitoring to track a live LLM endpoint

Subdomain 6.7: Identify evaluation judges that require ground truth

Subdomain 6.8: Use AI Gateway (Inference Tables, Usage Tables, and rate limiting) to track an LLM or agent deployed via Agent Framework

Subdomain 6.9: Use Databricks custom Scorers for evaluating agents and LLMs

Subdomain 6.10: Incorporate SME feedback to improve agent performance