Prepare and test your skills
Prepare and test your skills
Free sample question, answered and explained below. The Generative AI Leader practice bank has 2,191 more like it. Try 10 free: instant score, no account.
An enterprise is developing a generative AI agent to assist its customer support representatives. The architecture team needs to select the appropriate tooling mechanisms to enable three core capabilities:
Which agent tooling component should the enterprise configure specifically to ground the agent's responses in their private organizational documents?
Extensions are agent tools that connect generative AI models directly to external REST APIs and cloud services. They bridge the gap between large language models and operational systems by translating model intents into live API requests using standardized API schemas (such as OpenAPI specifications).
In modern agent architectures, extensions handle external system integration and action execution, whereas data stores handle knowledge retrieval and grounding.
Data stores are specialized agent tooling components designed to index, search, and retrieve information from structured and unstructured internal data repositories. They allow generative AI agents to access enterprise content—such as PDF documents, HTML pages, databases, and internal knowledge bases—to ground responses in accurate, domain-specific information.

Data stores provide a fully managed retrieval layer specifically engineered for knowledge discovery and grounding in enterprise documentation. While extensions and function calling enable agents to take actions and execute code, data stores are the dedicated mechanism for connecting agents to organizational document repositories.
Function calling is a capability of large language models where the model detects when a custom function should be invoked and generates structured arguments (typically formatted as a JSON object) matching a predefined function signature.
Function calling is often combined with data stores in complex agents: the agent uses data stores to answer knowledge questions and function calling to interact with proprietary local software components.
Code Interpreter is an execution tool within generative AI environments that enables the agent to dynamically generate and run programming code (such as Python) inside a sandboxed environment to perform mathematical calculations, data transformations, and visual chart generation.
Code Interpreter provides computational power to agents, while data stores provide the factual knowledge foundation required for organizational grounding.
Answer them yourself and get your score the moment you finish. No account needed.
Full access includes
Keep the momentum going with these hand-picked practice scenarios
Last updated