‹ All Google Cloud Generative AI Leader questions

GCP Generative AI Leader Practice Question 17: Agent Tooling Live Systems

Google Cloud Generative AI Leader · Test 2 · question 7 of 10

Google Cloud's Gen AI Offeringsmedium

An airline's new assistant answers baggage-allowance and change-fee questions well, because it was grounded in the published policy documents. Passengers, though, keep asking "where is my bag right now" and "move me to the 6pm flight", and the assistant either apologizes or invents an answer. The baggage tracking system and the reservation system both expose supported internal APIs that staff already use.

What capability does the assistant need in order to handle these requests?

Show answer and explanation

Answer:

C. Tools, so the model can call the airline's baggage and reservation APIs to fetch live data and take actions

Function calling, also known as tool use, gives the model definitions of external tools. When it processes a prompt the model determines whether a tool is needed and, if so, emits structured data naming the tool and its parameters; the application executes the call and feeds the result back. Google Cloud names the two use cases directly: fetching data (up-to-date information from APIs and systems) and taking action (submitting forms, updating state). "Where is my bag" is the first; "move me to the 6pm flight" is the second. Option C is the only one that bridges the assistant to live systems.

- A is wrong because a context window only holds what you put into the request. No window size lets a model read a tracking system it was never connected to. - B is wrong because grounding in more documents still only answers policy questions. Documents describe the rules; they don't know where one passenger's suitcase is right now. - D is wrong because fine-tuning adjusts style and task behavior, not access to data. A better-phrased answer about a live bag location is still a guess.

Reference: Introduction to function calling

Practice Test 2 ›

Study guides for Google Cloud Generative AI Leader

Google Cloud Digital Leader exam: what's on it, who it's forGoogle Cloud Digital Leader: August 2026 exam update, six sections, US$99 price as of November 2026, renewal, study plan and ACE comparison.

Agentic AI certification: Oracle, Google, GitHub, NVIDIAAgentic AI certifications in 2026: Oracle's free exam, GitHub GH-600, Google, NVIDIA and Claude, compared by status, price and role.

Google Cloud Generative AI Leader vs AWS AI PractitionerGoogle Cloud Generative AI Leader vs AWS AI Practitioner: format, cost, topics, free preparation and which certification to take first.

Best AI certifications 2026: AWS, Google, Microsoft, ClaudeThe best AI certifications in 2026 from AWS, Google, Microsoft, Claude and Databricks, by level, with price, status and which one to take first.

Google Cloud certification path: is ACE worth it?Is Google's Associate Cloud Engineer certification worth it? The Google Cloud certification path in 2026, with cost, format and which exam to take first.

Google Professional Agentic Architect: what it isGoogle's Professional Agentic Architect certification explained - beta status, the two-part exam, the five domains, price, validity and how to prepare.

What Is RAG? How Retrieval-Augmented Generation WorksWhat RAG is and how it works: chunking, embeddings, vector search, hybrid search, reranking, GraphRAG and agentic RAG on AWS, Google and Azure.

Google Cloud's generative AI offerings, mappedGemini app, Gemini for Workspace, Gemini Enterprise, Agent Search, the contact center suite and Agent Platform: which one a business should pick, and why.

Prompt engineering vs RAG vs fine-tuningWhen to use prompt engineering, retrieval-augmented generation, fine-tuning or continued pre-training, compared on cost, freshness, hallucination and privacy.