GES-C02 study guide · 2026

The 4 GES-C02 domains, explained

4 domains and 15 official objectives. Snowflake Gen AI Functions carries the most weight at 38%. Each guide explains what the domain covers, how its questions are framed and where candidates lose marks.

Start with Domain 2 See all domains
Questions
55
Time
85 minutes
Passing score
750 / 1000 (scaled)
Outline
GES-C02 study guide (current; released May 2026, replaced GES-C01)

Exam blueprint

Bar widths follow the official weights. Weight ranges are drawn at their midpoint.

  1. 1 18%
  2. 2 38%
  3. 3 29%
  4. 4 15%
  1. 1 Snowflake for Gen AI Overview
  2. 2 Snowflake Gen AI Functions
  3. 3 Snowflake Gen AI Governance
  4. 4 Snowflake Document Processing

All 4 domains

15 official objectives 35–51 hrs suggested study

  1. Domain 01 18%

    Snowflake for Gen AI Overview

    Domain 1 maps the Snowflake Gen AI landscape: Cortex AI functions, Cortex Search for retrieval, Cortex Analyst for text-to-SQL, Cortex Agents, Snowflake Intelligence, Cortex Code, cross-region inference, REST APIs, MCP and bringing your own models.

    Inside this domain

    • Define Snowflake's Gen AI principles and features.
    • Outline Gen AI capabilities in Snowflake.

    Watch for Search for metrics

    Objectives
    2
    Questions est.
    ~10
    Study time est.
    6–9 hrs
  2. Domain 02 38%

    Snowflake Gen AI Functions

    The heaviest GES-C02 domain. It covers the Cortex AI function families, vector and helper functions, RAG and text-to-SQL analysis, chat interfaces, Cortex functions inside data pipelines, and running third-party models with Snowpark Container Services and the Model Registry.

    Inside this domain

    • Apply AI functions in Snowflake.
    • Perform data analysis given a use case.
    • Build or interact with interfaces to chat with data in Snowflake.
    • Apply Snowflake Cortex functions in data pipelines.
    • and 1 more objectives

    Watch for Prompt everything

    Objectives
    5
    Questions est.
    ~21
    Study time est.
    14–20 hrs
  3. Domain 03 29%

    Snowflake Gen AI Governance

    Domain 3 covers governing Gen AI in Snowflake: restricting models, data safety and guardrails, REST API authentication, Cortex database roles and privileges, managing Cortex costs, and AI observability with evaluations, tracing and logging.

    Inside this domain

    • Set up model access controls.
    • Grant and revoke Role-Based Access Control (RBAC) and privileges.
    • Manage, monitor, and optimize Snowflake Cortex costs.
    • Use Snowflake AI observability tools.

    Watch for Grant only, never revoke

    Objectives
    4
    Questions est.
    ~16
    Study time est.
    10–14 hrs
  4. Domain 04 15%

    Snowflake Document Processing

    Domain 4 covers document processing with Cortex: AI_PARSE_DOCUMENT in OCR and LAYOUT modes, AI_EXTRACT with response formats, staging and preparing files, automated pipelines with streams and tasks, and troubleshooting errors, privileges, cost and arctic-extract fine-tuning.

    Inside this domain

    • Use document parsing functions.
    • Prepare and manage documents and implement extracting workflows.
    • Build automated document processing pipelines with Cortex AI integration.
    • Troubleshoot and optimize document processing.

    Watch for Old Document AI build

    Objectives
    4
    Questions est.
    ~8
    Study time est.
    5–8 hrs

Study the heaviest domains first

Marks follow weight. This order puts the most marks behind you first, across about 35–51 hrs of study.

  1. 2 Snowflake Gen AI Functions 38% · 14–20 hrs
  2. 3 Snowflake Gen AI Governance 29% · 10–14 hrs
  3. 1 Snowflake for Gen AI Overview 18% · 6–9 hrs
  4. 4 Snowflake Document Processing 15% · 5–8 hrs

Try one

Practice questionDomain 2: Snowflake Gen AI Functions

A retailer stores 5 million product reviews and needs to keep only those that describe a delivery problem before further analysis. Which SQL approach is MOST appropriate?

One trap from every domain

The answer that looks right, and the clue that gives it away.

  • Domain 1

    Search for metrics

    Clue Questions ask for totals, trends or comparisons over tables.

  • Domain 2

    Prompt everything

    Clue Output must be a fixed label or score.

  • Domain 3

    Grant only, never revoke

    Clue Only one team should be able to call Cortex.

  • Domain 4

    Old Document AI build

    Clue Exam answers mention AI_EXTRACT and arctic-extract.

Other Artificial Intelligence & Machine Learning certifications

Study guides for exams that overlap with GES-C02.

Practise what you read

GES-C02 domains: common questions

How many domains are in the GES-C02 exam?

GES-C02 has 4 domains with 15 official objectives between them: Snowflake for Gen AI Overview, Snowflake Gen AI Functions, Snowflake Gen AI Governance and Snowflake Document Processing.

Which GES-C02 domain carries the most weight?

Snowflake Gen AI Functions is the heaviest at 38%, followed by Snowflake Gen AI Governance (29%). The lightest is Snowflake Document Processing (15%). Weights come from Snowflake's official outline.

What is the GES-C02 exam format?

Questions: 55. Time allowed: 85 minutes. Passing score: 750 / 1000 (scaled).

How long should I study for GES-C02?

Our planning estimate is 35–51 hrs across all domains, split by weight. It is an editorial estimate, not an official figure, so adjust it to your experience and to how you score on practice questions.

Where should I start?

Start with Snowflake Gen AI Functions, because it carries the most marks, then work down by weight. Use the checklist on each domain page to confirm you can do what the domain asks before moving on.

Which outline is this guide based on?

This guide follows GES-C02 study guide (current; released May 2026, replaced GES-C01), published by Snowflake. It was last reviewed in October 2026.

Domain names, weights and objectives come from Snowflake's official outline (GES-C02 study guide (current; released May 2026, replaced GES-C01)). Question counts and study hours are editorial planning estimates, not official figures. Last reviewed October 2026.