SnowPro Specialty: Gen AI Preparation Details
The SnowPro Specialty: Gen AI (GES-C02) exam validates your ability to build, govern, and optimize generative AI solutions on Snowflake Cortex. This guide covers every domain, from Cortex Search and Analyst to Snowpark Container Services and Document Processing, with links to official documentation. You can also explore more Snowflake certification study guides on the Snowflake category page to keep building your skills.
SnowPro Specialty: Gen AI Materials
| Coursera | Introduction to Generative AI with Snowflake |
| Udemy | SnowPro Specialty: Gen AI Practice Tests 2026 |
Domain 1.0: Snowflake for Gen AI Overview
1.1 Define Snowflake’s Gen AI principles and features.
Snowflake Cortex (e.g., Cortex Models and Functions, Cortex Fine-tuning (Public Preview), Cortex Search (RAG use cases, Unstructured data use cases), Cortex Analyst (Text-to-SQL use cases), Cortex Agents)
Snowflake Cortex AI Functions (including LLM functions)
Fine-tuning (Snowflake Cortex)
Snowflake Cortex Code
Cortex Code in Snowsight UI (e.g., Cortex Code Command Line (CLI))
Cortex Code CLI Model Context Protocol (MCP) support
Snowflake Copilot Inline (Public Preview) (e.g., Cortex Models and Functions, Cortex Fine-tuning (Public Preview), Cortex Search (RAG use cases))
Using Snowflake Copilot inline
Snowflake Cortex AI Functions (including LLM functions)
Fine-tuning (Snowflake Cortex)
Snowflake Intelligence
Getting started with Snowflake CoWork
Nov 04, 2025: Snowflake Intelligence (General availability)
User access and settings for agents
Different interfaces (e.g., AI Studio, SQL, REST API)
Snowflake Cortex AI Functions (including LLM functions)
Bringing your own models into Snowflake (e.g., Snowflake Model Registry (custom model), Snowpark Container Services)
Bring your own model types via serialized files
1.2 Outline Gen AI capabilities in Snowflake.
Prompting
Cortex AI functions (e.g., Vector-embedding, Context Windows)
Snowflake Cortex AI Functions (including LLM functions)
Models and regional availability for Cortex AI Functions
Cortex Search (e.g., Multi-index queries, Access control requirements, Different ways to use Cortex Search)
Getting Started with Access Controls for RAGs (Cortex Search)
Cortex Analyst (e.g., Semantic Views, Semantic Views Autopilot, YAML Specification for Semantic Views, Verified Query, Custom Instructions)
YAML specification for semantic views
Cortex Analyst Verified Query Repository
Custom instructions in Cortex Analyst
Cortex Agents
Access control and authentication
Snowflake Intelligence
Getting started with Snowflake CoWork
Tutorial 3: Add a CKE to Snowflake Intelligence
Cross-region inference (e.g., CORTEX_ENABLED_CROSS_REGION parameter, Considerations (e.g., latency, availability))
August 08, 2024 — Cross-region inference for Snowflake AI & ML features — General Availability
Oct 16, 2025: Cross-region inference for US Commercial Gov
REST APIs
Access control and authentication
Model Context Protocol (MCP)
Cortex Code CLI Model Context Protocol (MCP) support
Snowflake Cortex Code (e.g., Cortex Code CLI commands)
Cortex Code CLI Model Context Protocol (MCP) support
Cortex Knowledge Extensions (CKE)
Tutorial 3: Add a CKE to Snowflake Intelligence
Domain 2.0: Snowflake Gen AI Functions
2.1 Apply AI functions in Snowflake.
Snowflake Cortex AI functions: General (e.g., AI_COMPLETE, COMPLETE Structured Outputs)
AI_COMPLETE structured outputs
Snowflake Cortex AI functions: Task-specific functions (e.g., AI_CLASSIFY, AI_EXTRACT, AI_PARSE_DOCUMENT, AI_SENTIMENT, SUMMARIZE, AI_SUMMARIZE_AGG, AI_TRANSLATE, AI_EMBED, AI_FILTER, AI_AGG, AI_SIMILARITY, AI_TRANSCRIBE, AI_REDACT)
Parsing documents with AI_PARSE_DOCUMENT
Snowflake Cortex AI functions: Vector functions (e.g., VECTOR_INNER_PRODUCT, VECTOR_L1_DISTANCE, VECTOR_L2_DISTANCE, VECTOR_COSINE_SIMILARITY, VECTOR_TRUNCATE, VECTOR_NORMALIZE, VECTOR_SUM, VECTOR_MIN, VECTOR_MAX, VECTOR_AVG)
Snowflake Cortex AI functions: Helper functions (e.g., AI_COUNT_TOKENS, TRY_COMPLETE, SPLIT_TEXT_RECURSIVE_CHARACTER, SPLIT_TEXT_MARKDOWN_HEADER, TO_FILE, PROMPT)
TRY_COMPLETE (SNOWFLAKE.CORTEX)
SPLIT_TEXT_RECURSIVE_CHARACTER (SNOWFLAKE.CORTEX)
SPLIT_TEXT_MARKDOWN_HEADER (SNOWFLAKE.CORTEX)
2.2 Perform data analysis given a use case.
Unstructured data: Functions (e.g., AI_PARSE_DOCUMENT, AI_EXTRACT, AI_SIMILARITY, AI_COMPLETE)
Parsing documents with AI_PARSE_DOCUMENT
Unstructured data: Cortex Search (e.g., Recursive split text markdown, Chunk sizing, Embedding models, Semantic reranking)
SPLIT_TEXT_RECURSIVE_CHARACTER (SNOWFLAKE.CORTEX)
Unstructured data: Multi-modal Analytics (e.g., Audio and Image Processing)
Structured data: Functions (e.g., AI_COMPLETE)
Models and regional availability for Cortex AI Functions
Structured data: Cortex Analyst (e.g., Cortex Analyst Verified Query Repository (VQR), Integration with Cortex Search, Suggested Questions, CUSTOM_INSTRUCTIONS)
Cortex Analyst Verified Query Repository
Suggestions for semantic models and views
Custom instructions in Cortex Analyst
Performance considerations (e.g., Choosing a model, Latency (e.g., model size), Accuracy (e.g., fine-tuning, reducing hallucinations), Model capability, Provisioned Throughput)
Models and regional availability for Cortex AI Functions
Fine-tuning (Snowflake Cortex)
AI Observability in Snowflake Cortex
2.3 Build or interact with interfaces to chat with data in Snowflake.
Set up the Snowflake environment (e.g., Required privileges)
Privileges and model access for Cortex AI Functions
Access control and authentication
User access and settings for agents
Invoke Cortex functions within the application code (e.g., Streamlit in Snowflake) (e.g., Chat conversations: Multi-turn architecture, Update parameters (i.e., messages array for conversation history))
Snowflake Intelligence
Getting started with Snowflake CoWork
2.4 Apply Snowflake Cortex functions in data pipelines.
Snowflake Cortex
Snowflake Cortex AI Functions (including LLM functions)
Introduction to streams and tasks
SQL interface
Snowflake Cortex AI Functions (including LLM functions)
Data extraction
Parsing documents with AI_PARSE_DOCUMENT
Data enrichment
Cortex AI Functions: Documents
Data augmentation
Data transformations
SPLIT_TEXT_RECURSIVE_CHARACTER (SNOWFLAKE.CORTEX)
2.5 Run third-party models in Snowflake.
Using Snowpark Container Services (e.g., Environment setup, Docker images, Specification files, Create compute pool, Create image repository)
Tutorial 1: Create a Snowpark Container Services Service
Service specification reference
Managing Snowpark Container Services (including service functions) with Python
Using Snowflake Model Registry (e.g., Logging the model, Calling the model)
Bring your own model types via serialized files
Managing models with the Snowflake Model Registry
Domain 3.0: Snowflake Gen AI Governance
3.1 Set up model access controls.
Limits on which models can be used (e.g., Restrict access to specific models, Application roles: Control model access (Role-Based Access Control (RBAC), Account-level allowlist parameter))
Privileges and model access for Cortex AI Functions
Apr 28, 2025: Role-Based Access Control for Cortex LLM Models
Snowflake Cortex AI Functions Model RBAC Rollout
Data safety and security considerations (e.g., Cross region inference, Guardrails, Sensitive data management (e.g., AI_REDACT), Methods to reduce model hallucinations and bias)
AI Observability in Snowflake Cortex
REST API authentication methods
Access control and authentication
3.2 Grant and revoke Role-Based Access Control (RBAC) and privileges.
Individual privileges (e.g., Specific requirements for Analyst, Search, Agents, and Snowflake Intelligence)
Privileges and model access for Cortex AI Functions
Access control and authentication
User access and settings for agents
Getting Started with Access Controls for RAGs (Cortex Search)
Roles (e.g., CORTEX_USER, CORTEX_ANALYST_USER, CORTEX_AGENT_USER, CORTEX_EMBED_USER)
Privileges and model access for Cortex AI Functions
Access control and authentication
3.3 Manage, monitor, and optimize Snowflake Cortex costs.
Cortex Agents (e.g., Limit token usage)
CORTEX_AGENT_USAGE_HISTORY view
Cortex Search (e.g., Different types of costs (e.g., virtual warehouse, EMBED_TEXT, serving, indexing))
CORTEX_SEARCH_DAILY_USAGE_HISTORY view
Monitor Cortex Search requests
Cortex Analyst
CORTEX_ANALYST_USAGE_HISTORY view
Cortex AI functions (e.g., Minimize tokens, Token cost implications)
CORTEX_AI_FUNCTIONS_USAGE_HISTORY view
Snowflake Cortex AI Functions (including LLM functions)
Tracking costs of Snowpark Container Services (e.g., Compute pools)
Managing Snowpark Container Services (including service functions) with Python
Tracking model usage and consumption (e.g., Usage quotas, CORTEX_ANALYST_USAGE_HISTORY, CORTEX_AISQL_USAGE_HISTORY, CORTEX_SEARCH_DAILY_USAGE_HISTORY, CORTEX_REST_API_USAGE_HISTORY, CORTEX_PROVISIONED_THROUGHPUT_USAGE_HISTORY, METERING_DAILY_HISTORY, METERING_HISTORY)
CORTEX_ANALYST_USAGE_HISTORY view
CORTEX_AI_FUNCTIONS_USAGE_HISTORY view
CORTEX_SEARCH_DAILY_USAGE_HISTORY view
Object tagging to monitor AI services costs
Introduction to object tagging
CORTEX_AI_FUNCTIONS_USAGE_HISTORY view
3.4 Use Snowflake AI observability tools.
Snowflake AI observability features (e.g., Evaluation metrics, Comparisons, Tracing, Logging, Event tables)
AI Observability in Snowflake Cortex
Snowflake AI Observability Reference
Implementation methods (e.g., Trulens SDK)
AI Observability in Snowflake Cortex
Snowflake AI Observability Reference
Domain 4.0: Snowflake Document Processing
4.1 Use document parsing functions.
AI_PARSE_DOCUMENT (e.g., OCR mode, LAYOUT mode, page_split, page_limit)
Parsing documents with AI_PARSE_DOCUMENT
Mar 19, 2025: Additional file format support for Cortex AI Parse Document
Cortex AI Functions: Documents
AI_EXTRACT (e.g., Response format, How to prompt/Prompt engineering)
Extracting information from documents with AI_EXTRACT
Fine-tuning arctic-extract models
4.2 Prepare and manage documents and implement extracting workflows.
Upload documents
Document Processing Playground
Requirements (e.g., formats, size limits)
Mar 19, 2025: Additional file format support for Cortex AI Parse Document
Parsing documents with AI_PARSE_DOCUMENT
4.3 Build automated document processing pipelines with Cortex AI integration.
Orchestration of Snowflake tooling (e.g., Streams, Tasks)
Introduction to streams and tasks
4.4 Troubleshoot and optimize document processing.
Extracting query errors (e.g., GET_PRESIGNED_URL function)
Parsing documents with AI_PARSE_DOCUMENT
Requirements and privileges
Privileges and model access for Cortex AI Functions
Parsing documents with AI_PARSE_DOCUMENT
Cost and best practice considerations
CORTEX_AI_FUNCTIONS_USAGE_HISTORY view
Fine-tuning arctic-extract models
Fine-tuning arctic-extract models
Extracting information from documents with AI_EXTRACT
Wrapping Up SnowPro Specialty: Gen AI
This guide has walked through all four domains of the SnowPro Specialty: Gen AI (GES-C02) exam, covering Cortex Search, Cortex Analyst, Snowpark Container Services, and Document Processing with official Snowflake documentation for every objective. With focused study and hands-on practice in Snowsight, you’ll be well prepared to earn this certification. You can also explore more Snowflake certification study guides on the Snowflake category page to keep building your skills. Have a question or tip? Leave a comment below.
Receive Updates on SnowPro Specialty: Gen AI Exam
Want to be notified as soon as I post? Subscribe to the RSS feed / leave your email address in the subscribe section. Share the article to your social networks with the below links so it can benefit others.
