Chapter 1 of 4 · Snowflake GES-C02
Snowflake for Gen AI
GES-C02 chapter overview of Snowflake for Gen AI: Cortex Search, Analyst, Agents, Code, Intelligence, AI functions, cross-region inference, REST and MCP.
- 13topics
- 53 minfast track
- 4diagrams and exhibits
- 18%of the exam
Topics in this chapter
Take them in order, or jump to the one you need.
- 1Gen AI Principles, Snowflake Cortex, Models and Fine-tuningSnowflake Gen AI principles, what Snowflake Cortex is, how Cortex models and AI functions are called, and what Cortex Fine-tuning…4 min
- 2Cortex Search for RAG and Unstructured DataWhat Cortex Search is, how its hybrid search works, how to create a service, and how it powers RAG and unstructured data use…4 min
- 3Cortex Analyst and Text-to-SQL Use CasesWhat Cortex Analyst is, how it turns business questions into SQL using semantic views, its access roles and limits, and the…4 min
- 4Cortex Agents and Cortex Code in Snowsight and the CLIWhat Cortex Agents are and which tools they use, plus Snowflake Cortex Code in the Snowsight UI and the command line, with the…4 min
- 5Copilot Inline, Snowflake Intelligence and the Gen AI InterfacesCopilot inline, Snowflake Intelligence and the interfaces to Cortex: AI Studio in Snowsight, SQL functions and the REST API, and…4 min
- 6Bringing Your Own Models: Model Registry and Snowpark Container ServicesBring your own models into Snowflake with the Model Registry and Snowpark Container Services: when to choose each, how models run…4 min
- 7Gen AI Capabilities: Prompting, AI Functions, Embeddings and Context WindowsOutline Snowflake Gen AI capabilities: prompting AI_COMPLETE, the Cortex AI functions, vector embeddings with AI_EMBED and…4 min
- 8Cortex Search Capabilities, Multi-Index Queries and Access ControlCortex Search capabilities: multi-index queries, filters and scoring, access control privileges, and the SQL, Python and REST…Diagram4 min
- 9Cortex Analyst Capabilities: Semantic Views, Autopilot, YAML, Verified Queries and InstructionsCortex Analyst capabilities: semantic views, Semantic View Autopilot, the YAML specification, verified queries and custom…4 min
- 10Cortex Agents and Snowflake Intelligence CapabilitiesCortex Agents capabilities: tools, orchestration, run API, threads, budgets and access control, plus what Snowflake Intelligence…Diagram4 min
- 11Cross-Region Inference and the CORTEX_ENABLED_CROSS_REGION ParameterCross-region inference for Cortex: the CORTEX_ENABLED_CROSS_REGION parameter, its values and default, who sets it, data handling…Diagram4 min
- 12Cortex REST APIs and the Model Context Protocol (MCP)The Cortex REST APIs for inference, search, Analyst and agents, and how a Snowflake-managed MCP server exposes Cortex tools to AI…Diagram4 min
- 13Cortex Code Capabilities, CLI Commands and Cortex Knowledge ExtensionsSnowflake Cortex Code capabilities, the cortex CLI commands and flags, and Cortex Knowledge Extensions that share licensed…5 min
About this chapter
What this chapter covers
Snowflake for Gen AI Overview is the map of everything Snowflake offers for generative AI. For the SnowPro Specialty Gen AI GES-C02 exam it tests choices, not definitions: which Cortex feature fits a scenario, which role or parameter turns it on, and which interface to call.
Questions are scenarios that start with "A Gen AI Specialist needs to ...". They are multiple choice or multiple select, and the right answer usually turns on one detail such as a role name, an endpoint, a default or the difference between two similar features.
How the topics fit together
Data stays in Snowflake. Cortex features sit on top of it, agents combine them, and interfaces and policies decide who can reach them and from where.
- Cortex building blocks are the AI functions, Cortex Search, Cortex Analyst and Cortex Agents.
- Developer and user experiences are Cortex Code, Copilot inline and Snowflake Intelligence.
- Your own models use the Model Registry and Snowpark Container Services.
- Reach and access cover REST APIs, MCP, privileges and cross-region inference.
- Shared knowledge covers Cortex Knowledge Extensions.
When two answers both look right, pick the one that fits the data type. Structured numbers point to Cortex Analyst, documents point to Cortex Search, and mixed questions point to a Cortex Agent.
How to use these pages
Each topic page has the same shape, so you can skim for what you need.
- What it is: the idea in plain words.
- How it works: the mechanism, with diagrams, SQL and comparison tables.
- Common mistakes: the classic traps.
- What to remember for the exam: the facts to memorize.
- Check yourself: three questions to test your understanding.
Read the pages in order the first time. Later pages build on the earlier ones.
Ready for more practice?
The full Snowflake GES-C02 question bank has 585 questions, with timed practice exams and an explanation for every answer.
This study guide is independent and is not affiliated with, endorsed by, or sponsored by Snowflake. Vendor names, certification names and exam codes are trademarks of their respective owners and are used for identification only.