Snowflake · GES-C01
SnowPro Specialty: Gen AI (GES-C01) Practice Tests
Validates expertise in applying generative AI and large language model (LLM) capabilities within the Snowflake platform. Assesses the ability to build, govern, and scale Gen AI solutions using Snowflake Cortex, Document AI, and related features.
Exam Details
Practice Questions
600
≈ 6 practice exams
Duration
85 minutes
Passing Score
750/1000
Difficulty
SpecialtyLast Updated
Jun 2026
Topics Covered
Snowflake for Gen AI OverviewSnowflake Gen AI & LLM FunctionsSnowflake Cortex LLMs and Cortex SearchSnowflake Gen AI GovernanceDocument AIModel Registry and SnowparkCortex Analyst and Agents
SnowPro Specialty: Gen AI (GES-C01) Practice Exam Preparation
Use this GES-C01 practice exam to prepare for SnowPro Specialty: Gen AI (GES-C01) with realistic questions, detailed explanations, and focused study modes. The practice bank includes 600 questions for Snowflake GES-C01, so you can review the exam steadily instead of relying on one long cram session.
As you practice, pay extra attention to recurring topics such as Snowflake for Gen AI Overview, Snowflake Gen AI & LLM Functions, Snowflake Cortex LLMs and Cortex Search, Snowflake Gen AI Governance, and Document AI. Start with short sessions to identify weak areas, then move into timed quizzes once your accuracy is consistent.
The explanations are especially useful when you want to connect exam wording to the responsibilities and scenarios described in the official certification guidance. Use the free preview first, then unlock the full question bank when you are ready to build a complete study routine.
Exam Domain Breakdown
Snowflake for Gen AI Overview26%
Snowflake Gen AI & LLM Functions40%
Snowflake Gen AI Governance22%
Document AI12%
Exam Overview
The SnowPro Specialty: Gen AI (GES-C01) certification validates specialized knowledge, skills, and best practices for leveraging generative AI and large language model (LLM) capabilities within the Snowflake Data Cloud. It assesses a candidate's ability to implement Snowflake Cortex AI features—including Cortex LLMs, Cortex Search, Cortex Analyst, and Cortex Agents—alongside Document AI, the Snowflake Model Registry, and Snowpark Container Services to build, govern, and scale production-grade Gen AI solutions.
The exam spans the full Gen AI development lifecycle on Snowflake: from applying task-specific and general-purpose LLM functions, constructing retrieval-augmented generation (RAG) pipelines and text-to-SQL workflows, to enforcing AI governance through access controls, guardrails, cost monitoring, and observability tooling. Candidates are also expected to understand how to run open-source and third-party models within the Snowflake environment. Note that GES-C01 is in the process of being retired in favor of its successor, GES-C02; candidates should review Snowflake's certification FAQs for transition details.
Who Should Take This Exam
This certification is designed for practitioners who build and operationalize AI-powered data applications on Snowflake. Primary target roles include AI/ML engineers constructing intelligent data pipelines, data scientists productionizing machine learning models, data engineers integrating Gen AI workflows into existing Snowflake architectures, and application developers adding AI-powered features to enterprise products.
Candidates are expected to have at least one year of hands-on Gen AI experience with Snowflake in an enterprise environment, along with foundational data engineering skills and SQL proficiency. Python coding experience is strongly beneficial, particularly for working with Snowpark and the Model Registry.
Prerequisites
Snowflake recommends that candidates hold an active SnowPro Associate: Platform or SnowPro Core certification before attempting GES-C01. This ensures a baseline understanding of Snowflake's core architecture, data loading, transformation patterns, and access control model before tackling Gen AI-specific content.
Beyond the certification prerequisite, candidates should have at least one year of practical Gen AI experience within Snowflake's enterprise environment. Proficiency in SQL and data engineering principles is assumed throughout the exam, and familiarity with Python is strongly advised for domains covering Snowpark, the Model Registry, and container-based model deployment.
Exam Format
The GES-C01 exam consists of 55 scored questions delivered in 85 minutes, yielding a per-question pace of roughly 90 seconds. Question types include multiple-choice, multiple-select, and scenario-based items that test applied judgment rather than rote recall. The exam is administered through Pearson VUE and is available as an online proctored or in-person test center experience.
Scoring is on a scale of 0–1000, with a passing score of 750 required. The exam fee is $225 USD (regional pricing variations may apply). The resulting certification is valid for two years, after which recertification is required. No unscored pilot questions have been publicly disclosed for this exam.
Skills Measured
- 1.Domain 1 – Snowflake for Gen AI Overview (26%): Covers foundational Gen AI principles on Snowflake, the Cortex platform ecosystem (LLMs, Search, Analyst, Fine-tuning, Agents, Copilot), security and privacy controls, role-based access control (RBAC) applied to AI resources, and available interfaces including SQL, REST API, and the Snowflake AI playground.
- 2.Domain 2 – Snowflake Gen AI & LLM Functions (40%): The most heavily weighted domain; focuses on applying Cortex general-purpose and task-specific LLM functions, vector operations and embeddings, helper functions, building RAG pipelines, text-to-SQL with Cortex Analyst, constructing chat interfaces, integrating Gen AI functions into data pipelines, and running third-party or open-source models via Snowpark Container Services and the Model Registry.
- 3.Domain 3 – Snowflake Gen AI Governance (22%): Emphasizes model access controls and policy enforcement, implementing AI guardrails, cost optimization strategies, monitoring LLM consumption via the CORTEX_FUNCTIONS_USAGE_HISTORY view, and leveraging AI observability tooling to audit and trace model behavior.
- 4.Domain 4 – Document AI (12%): Covers Snowflake Document AI capabilities for extracting structured information from unstructured documents, integrating document processing into Snowflake workflows, and applying governance controls to document-based AI pipelines.
Study Tips
- Download and read the official SnowPro Specialty: Gen AI Study Guide (PDF) from learn.snowflake.com before doing anything else—it defines the exact domain boundaries and lists the specific Cortex features, functions, and views you are expected to know.
- Prioritize Domain 2 (Snowflake Gen AI & LLM Functions, 40%) by completing hands-on labs in a Snowflake trial account: practice calling COMPLETE, SUMMARIZE, EXTRACT_ANSWER, SENTIMENT, and TRANSLATE functions directly in SQL, and build at least one end-to-end RAG pipeline using Cortex Search.
- For Domain 3 governance, study the CORTEX_FUNCTIONS_USAGE_HISTORY view in the Snowflake documentation and practice writing queries against it; also review how network rules, masking policies, and RBAC roles apply specifically to Cortex AI features.
- Use Snowflake University courses and the free-to-audit Snowflake courses on Coursera to cover Cortex Analyst, Cortex Agents, and the Model Registry—these newer features appear in both Domain 1 and Domain 2 and are underrepresented in third-party prep materials.
- For Document AI (Domain 4), work through Snowflake's official Quickstart guides on Document AI to understand how to configure build and query models for document extraction, since this domain's concepts are not covered by most generic ML study materials.
- Practice scenario-based questions by reviewing Snowflake developer blog posts and solution accelerators that show real enterprise Gen AI architectures—the exam favors applied judgment over memorization of parameter names.
- In the final week before the exam, take at least two full-length timed practice exams to calibrate your 85-minute pacing; flag any questions touching Cortex Fine-tuning or Snowpark Container Services for focused review, as these are frequently cited as weak spots.
Career Benefits
Earning the GES-C01 positions professionals at the intersection of enterprise data engineering and applied AI, a combination in high demand as organizations move from LLM experimentation to production deployment. Roles commonly associated with this certification include AI/ML Engineer, Data Science Engineer, Snowflake Platform Architect, and AI Solutions Engineer—all of which command strong compensation. Entry-level professionals with this credential can expect salaries in the $120,000–$155,000 range annually, mid-level specialists $155,000–$210,000, and senior practitioners $210,000 or higher, with top figures concentrated in major tech hubs such as San Francisco and Seattle.
Beyond compensation, the certification demonstrates platform-specific mastery that distinguishes candidates from those holding general cloud ML certifications (such as AWS MLS-C01 or Google Professional ML Engineer), as it validates hands-on ability with Snowflake's proprietary Cortex stack rather than generic ML frameworks. As Snowflake continues to expand its AI product surface—including Cortex Agents and fine-tuning—professionals certified on the platform are well positioned to lead Gen AI adoption initiatives within data-heavy enterprises.
Sample Questions
5 sample questions with answers and explanations. The full bank has 600 questions, enough for 6 full-length practice exams.
Preview — answers shown1. A business intelligence team at Northwind Retail has deployed Cortex Analyst to enable natural language querying of their sales data warehouse. Stakeholders report that any query requiring a join between the ORDERS table and the PRODUCTS table produces incorrect SQL with missing join conditions. The team's semantic model YAML already contains logical_tables, dimensions, facts, and metrics sections, but cross-table queries continue to fail. Which YAML attribute is missing from their semantic model configuration? (Select one!)
Arelationships, which defines predefined join paths between logical tables in the semantic model
Bmeasures, which specifies aggregation paths used for cross-table metric calculations
Ctable_links, which connects foreign key definitions to SQL generation rules
Dverified_queries, which stores example SQL queries for common multi-table join scenarios
Explanation
The relationships attribute in the Cortex Analyst semantic model YAML defines predefined join paths between logical tables. Without this attribute, Cortex Analyst cannot determine how to join tables like ORDERS and PRODUCTS when generating SQL for multi-table queries. The verified_queries repository improves accuracy for known query patterns but cannot substitute for explicitly defined join paths and does not resolve missing relationship definitions. Measures and table_links are not valid semantic model YAML attributes in Cortex Analyst's specification — omitting relationships is the direct cause of incorrect cross-table SQL generation.
2. A machine learning team at Contoso Research has developed a proprietary BERT-based model fine-tuned on biomedical literature for clinical named entity recognition. The model weights are stored as custom artifacts and require specific Python libraries and CUDA driver versions not available through Snowflake's standard function runtime. The team must run inference within Snowflake to satisfy data residency and governance requirements. Which Snowflake service should they use? (Select one!)
ASnowpark Container Services with a GPU compute pool running a containerized inference endpoint
BCortex Fine-Tuning using llama3-8b as the base model with the biomedical training dataset
CCortex Search configured with a custom embedding model that references the BERT model artifacts
DSnowflake Cortex COMPLETE() specifying the custom model artifact path as the first parameter
Explanation
Snowpark Container Services (SPCS) is the correct choice for deploying fully custom models with proprietary weights and non-standard runtime dependencies. SPCS allows containerized applications with GPU compute pools, enabling any arbitrary model architecture, library stack, and CUDA configuration to run within Snowflake's governance perimeter — satisfying data residency requirements. COMPLETE only supports Snowflake-hosted partner models from providers such as Mistral, Meta, and Anthropic; it does not accept file paths, external weights, or custom model artifacts as parameters. Cortex Fine-Tuning adapts existing supported base models by training on prompt-completion pairs stored in Snowflake tables; it cannot import external model architectures or incorporate proprietary BERT weights. Cortex Search is a managed retrieval service for unstructured document search — it is not a general-purpose inference runtime and does not support arbitrary custom ML models.
3. Fabrikam Industries has deployed a Cortex Agent that orchestrates calls to both Cortex Analyst for structured inventory data and Cortex Search for parts specification documents. During load testing, the team discovers that certain complex queries trigger long-running agent execution loops that consume large amounts of Snowflake credits before timing out naturally. Which TWO configuration options should the team set on the agent to prevent runaway executions from exceeding acceptable time and cost thresholds? (Select two!)
Multiple correct answersASet a maximum execution time limit on the agent configuration so the agent is terminated if it runs longer than the specified duration
BSet a maximum token budget on the agent configuration so the agent stops once the defined token limit is exhausted
CConfigure a maximum number of tool calls per agent session to cap the number of Cortex Analyst and Cortex Search invocations
DEnable Cortex Guard on the agent to detect and terminate unsafe or looping execution patterns
ESwitch the agent model from claude-sonnet to claude-haiku-4-5 to reduce per-token cost and limit execution time
Explanation
Cortex Agents support two built-in budget controls designed specifically to cap runaway executions: a time limit that terminates the agent if execution exceeds a specified duration, and a token limit that stops the agent once a defined token budget is exhausted. The agent halts as soon as either threshold is reached, providing both a time-based and a cost-based safety boundary. Configuring a maximum number of tool calls is not a native Cortex Agent budget parameter. Cortex Guard is a content safety control that screens agent inputs and outputs for harmful or unsafe content — it does not terminate agents based on execution duration or credit consumption. Switching to a smaller model reduces cost per token and may improve response speed, but does not prevent runaway loops because execution depth depends on the agent's reasoning path, not the model selected.
4. A multilingual document processing team at Tailspin Legal is building a RAG pipeline using Snowflake Cortex Search. Their legal contract corpus contains agreements averaging 10,000 tokens each, authored in 15 languages including Japanese, Arabic, and German. The team requires that complete documents be embedded as single units without chunking to preserve full document context. Which Snowflake embedding model should they select? (Select one!)
Asnowflake-arctic-embed-m-v1.5, which delivers the fastest embedding latency for high-volume processing
Bvoyage-multilingual-2, which provides a 32,000 token context window capable of embedding the full 10,000-token documents across all 15 languages
Csnowflake-arctic-embed-l-v2.0, which offers 1,024 dimensions with multilingual language support
Dsnowflake-arctic-embed-l-v2.0-8k, which provides an 8,192 token context window with multilingual capability
Explanation
voyage-multilingual-2 is the only Snowflake-supported embedding model with a context window large enough to embed 10,000-token documents without truncation, providing a 32,000 token context window. It also natively supports multilingual content, satisfying both requirements simultaneously. snowflake-arctic-embed-m-v1.5 is optimized for embedding speed with 768 dimensions but has a shorter context window that cannot accommodate 10,000-token documents without truncation. snowflake-arctic-embed-l-v2.0 offers 1,024 dimensions and multilingual support but does not provide an extended context window, meaning documents of this length would be truncated. snowflake-arctic-embed-l-v2.0-8k offers an 8,192 token context window with multilingual support, but its maximum context falls short of the 10,000-token document length, causing truncation that would compromise document integrity. Note that Snowflake generally recommends chunking documents to 512 tokens or fewer for optimal RAG retrieval quality, but when business requirements mandate full-document embedding, voyage-multilingual-2 is the only model capable of handling this document length without truncation.
5. A Snowflake administrator at Alpine Technologies is implementing governance controls for Cortex AI functions across a new multi-team deployment. The security team requires that only designated employees can invoke Cortex functions at all, and that the account is restricted to a small list of approved LLM models so no user can call COMPLETE with an unapproved model. Which two actions should the administrator take to satisfy both requirements? (Select two!)
Multiple correct answersAGrant the CORTEX_USER database role to the users and roles authorized to invoke Cortex AI functions
BCreate a row access policy on the SNOWFLAKE.CORTEX schema that restricts which functions specific users are allowed to call
CConfigure the CORTEX_MODELS_ALLOWLIST account parameter to specify the list of permitted LLM models
DEnable Cortex Guard on each database where Cortex functions are used to intercept and block calls to unauthorized models
ESet a custom network policy that blocks outbound connections to endpoints associated with unapproved model providers
Explanation
Granting the CORTEX_USER database role is the Snowflake-native access control mechanism that authorizes users to invoke Cortex AI functions. Without this role, or the equivalent AI_FUNCTIONS_USER database role, any attempt to call a Cortex function fails with an insufficient privileges error, satisfying the requirement that only designated employees can invoke functions. Configuring the CORTEX_MODELS_ALLOWLIST account parameter restricts which specific LLM models are accessible through COMPLETE and related Cortex functions at the account level, preventing any user from invoking unapproved models regardless of their other privileges, satisfying the model restriction requirement. Row access policies operate on table rows and columns, not on function invocation permissions, and cannot restrict which Cortex functions or models a user may call. Cortex Guard is a content safety and moderation feature that evaluates prompts and responses for harmful content such as prompt injection and unsafe outputs — it does not provide model selection control or function access restriction. Network policies in Snowflake control client access to the Snowflake service itself; they cannot selectively block specific internal Snowflake Cortex model endpoints, which are managed through the Snowflake governance framework rather than network-layer controls.
More Snowflake Practice Exams
SnowPro® Advanced: Data Scientist (DSA-C03)
DSA-C03 · 600 questions
SnowPro Advanced: Security Engineer (SEA-C01)
SEA-C01 · 550 questions
SnowPro Core Certification (COF-C03)
COF-C03 · 592 questions
SnowPro Specialty: Native Apps (NAS-C01)
NAS-C01 · 600 questions
SnowPro® Specialty: Snowpark (SPS-C01)
SPS-C01 · 599 questions
SnowPro Advanced: Administrator (ADA-C02)
ADA-C02 · 600 questions
$17.99
One-time access to this exam
600 questions (6 practice exams' worth)
Unlimited timed exam simulations
Yours forever — no subscription
Detailed explanations
Free preview stays available