Free Practice Questions for Snowflake GES-C01 Certification
Study with 449 exam-style practice questions designed to help you prepare for the Snowflake SnowPro Specialty: Gen AI (GES-C01). All questions are aligned with the latest exam guide and include detailed explanations to help you master the material.
Start Practicing
Random Questions
Practice with randomly mixed questions from all topics
Domain Mode
Practice questions from a specific topic area
Exam Information
Exam Details
Key information about Snowflake SnowPro Specialty: Gen AI (GES-C01)
Through Snowflake Continuing Education (CE) program (eligible Instructor-Led Training Courses or earning an equivalent/higher-level SnowPro Certification)
Active SnowPro Associate: Platform or SnowPro Core Certification
Candidates with 1+ years of Gen AI experience with Snowflake in an enterprise environment, advanced Python proficiency, and assumed data engineering and SQL knowledge. Roles include AI/ML Engineers, Data Scientists, Data Engineers, Data Application Developers, Data Analysts with programming experience.
10 – 13 hours
2 years
Exam Topics & Skills Assessed
Skills measured (from the official study guide)
Domain 1: Snowflake for Gen AI Overview
Subdomain 1.1: Define Snowflake’s Gen AI principles, features, and best practices.
• Snowflake Cortex - LLMs - Cortex Search - Cortex Analyst - Cortex Fine-tuning - Cortex Agents (Public Preview)
• Snowflake Copilot
• Security, privacy, access, and control principles - Role-Based Access Control (RBAC) - Guardrails - Required privileges - Cortex LLM Functions - Control model access
• CORTEX_MODELS_ALLOWLIST parameter
• Different interfaces - Cortex LLM Playground (Public Preview) - SQL - REST API
• Different ways of bringing your own models into Snowflake (for example, from Hugging Face) - Using Snowflake Model Registry (custom model) - Using Snowpark Container Services
Subdomain 1.2: Outline Gen AI capabilities in Snowflake.
• Cortex LLM functions (for example, task-specific, general) - Vector-embedding - Fine-tuning
• Cortex Search - RAG use cases - Unstructured data use cases - REST APIs
• Cortex Analyst - Semantic model generation - Stored in YAML files in a stage - Stored natively in semantic views (Public Preview) - Structured/text-to-SQL use cases - REST APIs
• Cortex Agents (Public Preview) - REST APIs
• Cross-region inference - CORTEX_ENABLED_ CROSS_REGION parameter - Considerations (for example, latency, availability)
Domain 2: Snowflake Gen AI & LLM Functions
Subdomain 2.1: Apply Gen AI and LLM functions in Snowflake.
• Snowflake Cortex - General - COMPLETE - COMPLETE Structured Outputs - Task-specific functions - CLASSIFY_TEXT - EXTRACT_ANSWER - PARSE_DOCUMENT - SENTIMENT - SUMMARIZE - TRANSLATE - EMBED_TEXT_768 - EMBED_TEXT_1024
• Cortex Search
• Cortex Analyst
• Cortex Fine-tuning
• Cortex Agents (Public Preview)
• Vector functions - VECTOR_INNER_ PRODUCT - VECTOR_L1_DISTANCE - VECTOR_L2_DISTANCE - VECTOR_COSINE_ SIMILARITY
• Helper functions - COUNT_TOKENS - TRY_COMPLETE - SPLIT_TEXT_ RECURSIVE_CHARACTER
• Choosing a model - Considerations (e.g. capability, latency, and cost)
Subdomain 2.2: Perform data analysis given a use case.
• Use fully-managed LLMs, RAG, and text-to-SQL services - Unstructured data - CORTEX PARSE_DOCUMENT - Structured data - Cortex Analyst - Cortex Analyst Verified Query Repository (VQR) - Integration with Cortex Search - Suggested Questions - Custom_ instructions field
• Performance considerations - Latency (for example, fine-tuning, model size)
Subdomain 2.3: Build chat interfaces to interact with data in Snowflake.
• Set up the Snowflake environment - Required privileges
• Invoke Cortex functions within the application code (for example, Streamlit)
• Chat conversations - Multi-turn architecture - Update parameters
Subdomain 2.4: Use Snowflake Cortex functions in data pipelines.
• Snowflake Cortex - SQL interface - Extracting data from text using COMPLETE - Transcripts - Data enrichment - Data augmentation - Data transformations
Subdomain 2.5: Run third-party models in Snowflake.
• Using Snowpark Container Services - Environment setup - Docker images - Specification files - Create compute pool - Create image repository
• Using the Snowflake Model Registry - Logging the model - Calling the model
Domain 3: Snowflake Gen AI Governance
Subdomain 3.1: Set up model access controls.
• Limits on which models can be used - Restrict access to specific models - CORTEX_MODELS_ ALLOWLIST parameter - Cortex LLM REST API - COMPLETE (SNOWFLAKE. CORTEX) - TRY_COMPLETE (SNOWFLAKE. CORTEX) - Cortex LLM Playground (Public Preview)
• Data safety and security considerations - Is data leaving/going to LLMs?
• REST API authentication methods
Subdomain 3.2: Set guardrails to filter out harmful or unsafe LLM responses.
• Cortex Guard - COMPLETE arguments
• Methods to reduce model hallucinations and bias
• Error conditions
Subdomain 3.3: Monitor and optimize Snowflake Cortex costs.
• Cortex Search - Different types of costs (virtual warehouse, EMBED_TEXT , Serving)
• Cortex Analyst - Snowflake Service Consumption Table
• Cortex LLM functions - Minimize tokens - Token cost implications
• Tracking model usage and consumption - Usage quotas - CORTEX_FUNCTIONS_USAGE_HISTORY view - CORTEX_FUNCTIONS_ QUERY_USAGE_HISTORY view
Subdomain 3.4: Use Snowflake AI observability tools.
• Snowflake AI observability (Public Preview) features - Evaluation metrics - Comparisons - Tracing - Logging - Event tables
• Implementation methods - Trulens SDK
Domain 4: Snowflake Document AI
Subdomain 4.1: Set up Document AI.
• Virtual warehouse, database, and schema considerations
• Roles and privileges - USAGE - OPERATE - CREATE SNOWFLAKE.ML. DOCUMENT_ INTELLIGENCE - CREATE MODEL
Subdomain 4.2: Prepare documents for Document AI.
• Upload documents
• Train the model
• Requirements (for example, formats, size limits)
• Question optimization best practices
Subdomain 4.3: Extract values from documents using Document AI.
• Conditions
• <model_build_ name>!PREDICT query
• Automation of data pipelines
Subdomain 4.4: Troubleshoot Document AI given a use case.
• Extracting query errors
• GET_PRESIGNED_URL function
• Requirements and privileges
• Cost and best practices considerations
Techniques & products