Snowflake · SF-GAI · Intermediate

SnowPro Specialty: Gen AI (GES-C02) — Practice Questions and Mock Exam

Name: Pass-IT
Author: Pass-IT

Prepare for SF-GAI with original practice questions and clear answer explanations. Ask Alex, your AI tutor, when you need more detail, use your results to identify topics to review, and practice your pacing with timed mock exams.

Start practicing SF-GAI free Buy SF-GAI access for $29.99

Buy SF-GAI access for $29.99 Start practicing SF-GAI free

55Mock exam questions

85minTime limit

750/ 1000Passing score

Checked against Snowflake · August 2026 · Current exam version

Overview

About the exam

The SnowPro Specialty: Gen AI Certification (GES-C02) validates specialized knowledge of generative AI on Snowflake: the Cortex suite of AI features and functions, including Cortex Analyst, Cortex Search and Cortex Code; Gen AI governance across infrastructure, data and cost; document processing; and building and fine-tuning open-source models with Snowpark Container Services and the Snowflake Model Registry. It tests the ability to meet customer use cases natively on the platform.

This specialty certification is for AI and ML engineers, data scientists, data engineers and data application developers with one or more years of Gen AI experience with Snowflake in an enterprise environment. Proficiency writing code in Python helps, and previous data engineering and SQL knowledge is assumed.

Try the practice preview

Try five SF-GAI questions

Try five practice questions from the app’s current SnowPro Specialty: Gen AI (GES-C02) question bank, with answers and explanations.

Snowflake Gen AI Governance1 / 5

By default, the USE AI FUNCTIONS privilege is granted to which role?

AlexFull explanation from Alex

PUBLIC USE AI FUNCTIONS: account-level privilege. Revokable by ACCOUNTADMIN only. Users need BOTH this AND CORTEX_USER or AI_FUNCTIONS_USER database role. Does not apply inside Snowflake native applications. SNOWFLAKE.CORTEX_USER: database role in SNOWFLAKE database. Covers all Covered AI features (Analyst, Search, Fine-tuning, Agent). Cannot be granted directly to users — must be granted to roles.

Sourcedocs.snowflake.com

Snowflake for Gen AI Overview2 / 5

Where are all large language models used by Snowflake Cortex AI Functions hosted?

AlexFull explanation from Alex

Fully hosted within Snowflake's infrastructure, keeping data secure and in place Data never leaves Snowflake's governance boundary. No third-party endpoints or external API calls. Ensures data security, governance, and scalability while keeping data in place. Models from OpenAI, Anthropic, Meta, Mistral, DeepSeek all run within Snowflake. Snowpark Container Services (SPCS): OCI-compliant container runtime in Snowflake.

Sourcedocs.snowflake.com

Snowflake Gen AI Functions3 / 5

A company wants to use Cortex Analyst but needs to ensure that no data or metadata leaves Snowflake's governance boundary. Which statement is correct?

AlexFull explanation from Alex

By default, Cortex Analyst uses Snowflake-hosted LLMs, ensuring no data leaves Snowflake's govern... All Cortex AI models are fully hosted within Snowflake infrastructure. Data never leaves Snowflake's governance boundary. No third-party endpoints or external API calls. Ensures data security, governance, and scalability while keeping data in place. Models from OpenAI, Anthropic, Meta, Mistral, DeepSeek all run within Snowflake.

Sourcedocs.snowflake.com

Snowflake for Gen AI Overview5 / 5

A data engineer needs to build a RAG pipeline in Snowflake that processes PDF documents, indexes them for semantic search, and generates contextual responses. Which sequence of Cortex AI functions and services should they use?

AlexFull explanation from Alex

A Snowflake RAG pipeline generally converts source documents into searchable text, retrieves relevant chunks, and passes that context to an LLM. For PDFs in Snowflake, AI_PARSE_DOCUMENT handles extraction, Cortex Search Service indexes and retrieves relevant content, and AI_COMPLETE generates contextual answers. The other sequences use functions for classification, sentiment, extraction, summarization, filtering, or redaction rather than the core RAG flow.

Sourcedocs.snowflake.com

Create a free account

Question pool

437 practice questions

The Pass-IT question pool gives you material to practice for SF-GAI. A Pass-IT mock exam uses 55 questions and a 85-minute time limit; these are practice settings.

Pool details: SF-GAI

Exam details checked against SnowflakeAugust 14, 2026

date of the last check against the official Snowflake source

Passing score750 / 1,000

as published by Snowflake

Objectives in the guide19 objectives listed in the official guide

across 4 domains in the official exam guide

Pool size437 questions

= The pool size is equivalent to 7 sets of 55 questions; this does not mean that each mock exam uses a separate set.

Blueprint domains4 domains in the exam blueprint

Snowflake for Gen AI Overview 76 · Snowflake Gen AI Functions 159 · Snowflake Gen AI Governance 136 · Snowflake Document Processing 66

Recorded as checked against sources437 of 437

questions recorded as having their answer, options, and explanation checked against official Snowflake documentation

How questions are made →

Exam domains

What's on the exam

Snowflake Gen AI Functions dominates the blueprint at 38%, covering the Cortex AISQL surface end to end: AI_COMPLETE and the task-specific functions (AI_CLASSIFY, AI_EXTRACT, AI_SENTIMENT, AI_TRANSLATE, AI_REDACT), the vector functions behind embeddings and similarity, Cortex Analyst and Cortex Search, and running third-party models through Snowpark Container Services and the Model Registry. Governance follows at 29%: model access control, the CORTEX_USER family of roles, guardrails, cost tracking through the Cortex usage-history views, and AI observability with TruLens. The overview domain takes 18%, spanning Cortex Code, Snowflake Intelligence, cross-region inference and MCP, and Document Processing closes at 15% with AI_PARSE_DOCUMENT modes, AI_EXTRACT prompting, and Streams-and-Tasks pipelines.

Functions and governance together are two-thirds of the exam, and that split is the tell: Snowflake is testing whether you can ship a Cortex workload somebody else has to pay for and audit, not whether you can name features. The guide describes scenario-based and interactive questions, and it assumes SQL and data-engineering knowledge plus Python before you start — the Gen AI vocabulary is the smaller half of the preparation.

Exam blueprint: SF-GAI

Snowflake for Gen AI Overview18%

Define Snowflake's Gen AI principles and outline Gen AI capabilities across the platform, including Snowflake Intelligence and Cortex Code.

≈ 9 h

Snowflake Gen AI Functions38%

Apply AI functions in Snowflake, perform data analysis for a given use case, build or interact with interfaces, apply Cortex functions, and run third-party models.

≈ 19 h

Snowflake Gen AI Governance29%

Set up model access controls, grant and revoke role-based access, and manage, monitor and optimise Gen AI workloads.

≈ 14 h

Snowflake Document Processing15%

Use document parsing functions (AI_PARSE_DOCUMENT, AI_EXTRACT), prepare and manage documents, build automated pipelines with Streams and Tasks, and troubleshoot extraction.

≈ 8 h

Format

Exam format and question types

The exam consists of 55 questions in 85 minutes. Question types are multiple select and multiple choice. Questions cover four domains: Snowflake Gen AI Functions (38%), Snowflake Gen AI Governance (29%), Snowflake for Gen AI Overview (18%), and Snowflake Document Processing (15%). A passing score is 750 on a scale of 0 to 1000. At roughly 1.5 minutes per question, pacing is tight for scenario-based AI questions.

Question types: SF-GAI

Multiple Choice70%

Select the single answer that best meets the question’s requirements.

Multiple Response30%

Select multiple answers. Follow the question’s instructions on how many to choose.

See Snowflake for official question-format information. The shares shown describe the Pass-IT practice pool; they do not establish the proportions on the official exam.

Planning

Preparing for SF-GAI

Delivered by online proctoring or at an onsite testing center, in English. There is no prerequisite certification. The certification expires two years after your issue date; you recertify through the Snowflake Continuing Education program with an eligible instructor-led training course or an equivalent or higher-level SnowPro certification.

Preparation and logistics: SF-GAI

Preparation

Illustrative study time30–75 h

illustrative planning range: 30 h with relevant experience to 75 h when starting out; your needs may fall outside this range

LevelIntermediate

Recommended backgroundNo prerequisites. One or more years of Gen AI experience with Snowflake in an enterprise environment recommended. Proficiency writing code in Python is helpful, and previous data engineering and SQL knowledge is assumed.

Taking and maintaining the certification

DeliveryOnline proctored or onsite testing centers.

Retake policyLimit of 4 attempts in a 12-month period. After three attempts Snowflake recommends attending an onsite Snowflake training course. Each registration requires the full registration fee.

Certification validity2 years

Snowflake certifications expire two years after the issue date. Recertify through the Snowflake Continuing Education (CE) program: complete an eligible Snowflake Instructor-Led (ILT) training course, or earn an equivalent or higher-level SnowPro certification. A valid certification is required to take part in the CE program.

Official guideView on provider site

Study notes

Common pitfalls

Topics to review: SF-GAI

01Cortex COMPLETE vs External
Not understanding when to use Cortex COMPLETE (native, serverless) versus calling external LLM APIs and the trade-offs of each approach leads to architecture question errors.
02RAG Pipeline Design
Confusing embedding generation, vector storage, similarity search, and context injection steps in a RAG pipeline causes retrieval-augmented generation question failures.
03Vector Data Types
Not understanding Snowflake VECTOR data type, distance metrics (cosine, inner product, L2), and how vector search integrates with Cortex leads to embedding question mistakes.
04Fine-Tuning vs Prompting
Not knowing when fine-tuning is appropriate versus few-shot prompting or RAG — and the cost and data requirements of each — leads to wrong solution design answers.

Practice with questions and explanations in Pass-IT →

Questions

Frequently asked questions

How long is the SnowPro Specialty: Gen AI (GES-C02) exam?

The SnowPro Specialty: Gen AI (GES-C02) exam has 55 questions and a 85-minute time limit.

What is the passing score for SnowPro Specialty: Gen AI (GES-C02)?

The passing score for the SnowPro Specialty: Gen AI (GES-C02) exam is 750 / 1000.

Which pitfalls should I review when preparing for SnowPro Specialty: Gen AI (GES-C02)?

Topics to review include Cortex COMPLETE vs External, RAG Pipeline Design, Vector Data Types, Fine-Tuning vs Prompting. Work through examples to check that you understand the distinctions and can explain your answer.

Which SnowPro Specialty: Gen AI domains carry the most weight?

Snowflake Gen AI Functions is the largest domain at 38%, ahead of Gen AI Governance at 29%. The platform overview takes 18% and document processing 15%. Two thirds of the exam therefore sit in the Cortex functions and the governance around them, which is where study time pays.

What do you need before the SnowPro Specialty: Gen AI exam?

No certification is required first. Snowflake recommends a year or more of Gen AI work with Snowflake in an enterprise environment, and assumes you already bring data engineering and SQL knowledge. Python helps, because the blueprint covers building and fine-tuning open-source models with Snowpark Container Services and the Model Registry.

How is the SnowPro Specialty: Gen AI exam structured?

55 questions in 85 minutes, multiple choice and multiple select, scored from 0 to 1000 with 750 to pass. That is roughly a minute and a half per question, which is tight for scenario items that describe a whole pipeline before they ask anything. Snowflake delivers it online with a proctor or at a testing centre, in English.

How long does SnowPro Specialty: Gen AI stay valid?

Two years from the issue date. You recertify through Snowflake's continuing education programme: an eligible instructor-led course, or an equivalent or higher-level SnowPro certification. That route is only open while your certification is still valid, so the two-year date is the one to diarise.

One certification, 12 months

Practice for SF-GAI

Focus your practice on one certification, or choose Pro to practice across all certifications.

Buy SF-GAI access for $29.99

Start a free practice sessionTry the first 20 questions without a card to see whether the practice suits you.

For eligible purchases: money-back guarantee if you fail your exam.

View guarantee terms →