You will notice the above features in the Snowflake GES-C02 Web-based format too. But the difference is that it is suitable for all operating systems. There is no need to go through time-taking installations or agitating plugins to use this format. It will lead to your convenience while preparing for the SnowPro Specialty: Gen AI Certification Exam (GES-C02) certification test. Above all, it operates on all browsers.
| Section | Weight | Objectives |
|---|---|---|
| Topic 1: Snowflake for Gen AI Overview | 24% | - Snowflake Cortex AI capabilities
|
| Topic 2: Document Processing | 10% | - Document AI processing
|
| Topic 3: Snowflake Cortex AI and LLM Functions | 38% | - Building generative AI applications
|
| Topic 4: Snowflake Gen AI Governance | 18% | - Access control and security
|
| Topic 5: Snowpark Container Services for Gen AI | 10% | - Custom model deployment
|
>> Reliable Snowflake GES-C02 Exam Topics <<
A free demo of the SnowPro Specialty: Gen AI Certification Exam (GES-C02) practice material is available at Easy4Engine. You are welcome to try a free demo to remove your doubts before buying our SnowPro Specialty: Gen AI Certification Exam product. Furthermore, a 24/7 customer support team of Easy4Engine is available. If you have any questions in your mind about our GES-C02 Study Material, feel free to contact us.
NEW QUESTION # 27
Which Cortex functions support a parameterized option that can be used to filter unsafe and harmful responses from LLMs? (Choose two)
Answer: A,E
Explanation:
Snowflake integrates Cortex Guard-an automated safety filtering layer built on Llama Guard-to intercept and filter unsafe or harmful model outputs before they are returned to the caller.
Cortex Guard is enabled by setting `'guardrails': true` inside the optional configuration object argument. This option is supported exclusively on general-purpose completion functions:
1. `SNOWFLAKE.CORTEX.COMPLETE()`
2. `SNOWFLAKE.CORTEX.TRY_COMPLETE()`
Because these functions generate open-ended natural language completions from arbitrary user prompts, they carry the risk of producing harmful, unsafe, or policy-violating content. Enabling guardrails on either function routes the generated output through the safety filter.
In contrast, task-specific functions-such as `TRANSLATE()`, `CLASSIFY_TEXT()`, and `SUMMARIZE()
`-run on constrained, specialized models designed for specific transformations and do not expose the
`guardrails` configuration parameter.
References & Study Guide Topics:
* Snowflake Gen AI Functions: Cortex Guard Safety Integration
* Content Moderation: Parameterized Guardrails in `COMPLETE` and `TRY_COMPLETE`
NEW QUESTION # 28
Which governance principles does Snowflake guarantee when its Gen AI features and the underlying models are used? (Choose two)
Answer: A,E
Explanation:
Snowflake Cortex AI operates strictly inside Snowflake's secure Data Cloud governance boundary, adhering to comprehensive enterprise trust principles. Under Snowflake's core AI governance framework, customer data, prompts, and completions are never utilized to train or fine-tune third-party foundation models, nor are they ever shared with model providers or other Snowflake accounts. All inference operations execute completely within Snowflake's managed trust perimeter.
Furthermore, Snowflake natively enforces its enterprise Role-Based Access Control (RBAC) across all Generative AI infrastructure and models. Access to specific Cortex LLM functions, proprietary models, and Model Registry artifacts requires explicit object and database-level grants (such as SNOWFLAKE.
CORTEX_USER and designated model roles), ensuring unified administrative oversight across all AI workloads.
Option C is incorrect because fine-tuned models remain private to the host Snowflake account and cannot be shared across disparate consumer accounts. Option D is incorrect because foundation models are deployed as serverless functions or containerized services without requiring direct account-level ingestion of external models exclusively via the Model Registry. Option E is incorrect because Cortex Guard is an optional evaluation parameter, not a mandatory feature.
References & Study Guide Topics:
* Snowflake Gen AI Governance: Data Privacy, Security Boundaries, and Trust Architecture
* Enterprise Security: Model Access Governance and Role-Based Access Control (RBAC)
NEW QUESTION # 29
The following error is received while attempting to extract details from a document with Snowflake Document AI:
`Request failed for external function DOCUMENT_EXTRACT_FEATURES$V1 with remote service error:
422`
How should this error be resolved?
Answer: B
Explanation:
When training and deploying custom extraction pipelines in Snowflake Document AI, a model build must transition through distinct development phases: drafting, fine-tuning, and publication.
During development, users annotate documents and define extraction values within the Document AI studio.
However, invoking the underlying programmatic scoring engine (which surfaces behind the scenes as
`DOCUMENT_EXTRACT_FEATURES$V1` or ` < model_name > !PREDICT`) against uncommitted builds triggers an HTTP 422 (Unprocessable Entity) remote service error. This occurs because the model build is still in a draft state and has not been compiled into an active, callable deployment artifact.To resolve this issue, the engineer must explicitly **publish** the model build within Snowsight (or complete the build lifecycle). Publishing freezes the annotated schema, provisions the serving endpoints, and registers the operational version so that SQL queries can execute inference. Privilege deficiencies return authorization errors (e.g., 403 or Access Denied) rather than remote service error 422.References & Study Guide Topics:* Snowflake Document Processing: Document AI Model Build Lifecycle* Troubleshooting: Publishing Document AI Models and Resolving 422 Extraction Errors===============
NEW QUESTION # 30
A Gen AI Specialist is creating metadata for Snowflake Cortex Analyst by creating a semantic model. The relationship between the PRODUCTS and PRODUCT_SALES tables is defined as:
```yaml
relationships:
- name: sales_to_products
join_type: left_outer
relationship_type: many_to_one
left_table: PRODUCT_SALES
relationship_columns:
- left_column: PRODUCT_ID
right_column: ID
right_table: PRODUCTS
```
Which join will Cortex Analyst generate in a query that uses this model?
```sql
Answer: D
Explanation:
Snowflake Cortex Analyst relies on the `relationships` section of a semantic model YAML specification to determine how logical tables must be joined when generating SQL.
The relationship definition contains key parameters that control join construction:
* `left_table: PRODUCT_SALES` designates the base table to be preserved in an outer join.
* `right_table: PRODUCTS` designates the lookup table joined to the preserved dataset.
* `join_type: left_outer` instructs Cortex Analyst to emit ANSI `LEFT OUTER JOIN` syntax preserving all records from the left table.
* `relationship_columns` maps `left_column: PRODUCT_ID` to `right_column: ID`, defining the join equality condition: `ON S.PRODUCT_ID = P.ID`.
Based on these metadata declarations, whenever a natural language query requires attributes spanning both tables, Cortex Analyst constructs the query starting from `PRODUCT_SALES AS S`, applies a `LEFT OUTER JOIN` to `PRODUCTS AS P`, and predicates the join condition using `ON S.PRODUCT_ID = P.ID`.
Options B, C, and D are incorrect because they invert table positions, employ `FULL OUTER JOIN` syntax, or place join conditions into a `WHERE` clause.
References & Study Guide Topics:
* Snowflake Gen AI Functions: Cortex Analyst Semantic Modeling Specifications
* Semantic Relationships: Defining Joins, Dimensional Cardinality, and Foreign Keys
NEW QUESTION # 31
When creating a Snowflake Document AI model, which object must have the CREATE SNOWFLAKE.ML.
DOCUMENT_INTELLIGENCE privilege?
Answer: B
Explanation:
Snowflake Document AI leverages zero-shot and fine-tuned multimodal models (specifically the Arctic-TILT architecture) to extract discrete data attributes from unstructured documents. Within Snowflake's object hierarchy, Document AI model builds (DOCUMENT_INTELLIGENCE objects) are managed as first-class, schema-level database entities.
Consequently, to initiate, build, and register a new Document AI pipeline within a target namespace, the user's active role must hold the CREATE SNOWFLAKE.ML.DOCUMENT_INTELLIGENCE privilege on the specific schema where the model build is instantiated (GRANT CREATE SNOWFLAKE.ML.
DOCUMENT_INTELLIGENCE ON SCHEMA < database > . < schema > TO ROLE < role > ;).
Securing database-level permissions provides container traversal (USAGE), but schema-level authority is required to instantiate schema-scoped ML assets. Virtual warehouses provide execution compute rather than metadata creation privileges, and stages serve as raw file storage repositories where stage-level privileges (READ, WRITE) govern file I/O rather than machine learning object creation. Without this explicit schema grant, attempts to initialize a Document AI build via Snowsight or SQL fail with authorization errors.
References & Study Guide Topics:
* Snowflake Document Processing: Document AI Workspace Setup and Permissions
* Object-Level Access Control: Schema Privileges for DOCUMENT_INTELLIGENCE
NEW QUESTION # 32
......
For candidates who are going to buying GES-C02 training materials online, you may pay more attention to the privacy protection. We respect the private information of you. If you choose us, we can ensure you that your personal information such as your name and email address will be protected well. Once the order finishes, your personal information will be concealed. Besides, GES-C02 Exam Materials contain both questions and answers, and it’s convenient for you to have a check of answers. We have online and offline chat service for GES-C02 exam materials, if you have any questions, you can have a conversation with them.
GES-C02 Valid Test Registration: https://www.easy4engine.com/GES-C02-test-engine.html