Section 1: Building agents using low-code tools

Question 1, 1.1 Configuring agentic workflows and behavior using low-code tools

An insurer's Dialogflow CX claims flow, now reused from CX Agent Studio as a flow-based agent, has 14 pages that collect incident details. Product owners want callers to be able to say "cancel my claim" on any page of the flow and be taken to the flow's Cancel Claim page. The team wants a single place to maintain this behavior and does not want to edit every page whenever the flow changes. What should you do?

1. Add a cancel_claim intent route, targeting the Cancel Claim page, to the flow start page as a flow-level route.
2. Add a condition-only route to the flow start page that checks a cancel_requested session parameter and transitions to the Cancel Claim page.
3. Add an identical cancel_claim intent route, targeting the Cancel Claim page, to each of the 14 pages so every page handles it explicitly.
4. Create an agent-level route group containing the cancel_claim intent route that targets the Cancel Claim page, and reference it from the flow.

Question 2, 1.1 Configuring agentic workflows and behavior using low-code tools

A telecom's CX Agent Studio application has a root agent and a Payments sub-agent. Security requires that the conversation must never be transferred to Payments until a verification tool has set the boolean variable is_verified to true. The rule must be enforced deterministically, and the business analysts who maintain the agent do not write Python. Instruction-only guidance was already tried and occasionally failed in testing. What should you configure?

1. Add a sentence to the root agent's instructions stating that it must never call {@AGENT: Payments} unless the {is_verified} variable is true, and repeat it in global instructions.
2. Write a before_agent_callback on the Payments agent that returns a refusal message whenever is_verified is false.
3. Create a handoff rule that blocks the transfer by using the advanced code option with a should_trigger_transfer_callback function.
4. Create a handoff rule from the root agent to Payments that blocks the transfer until the variable is_verified equals true.

Question 3, 1.1 Configuring agentic workflows and behavior using low-code tools

An electronics company wrote three pages of free-form prose instructions for a CX Agent Studio warranty agent. In testing, the agent sometimes approves a claim before it checks the purchase date, and it mixes the persona guidance with the hard rules. The team wants the agent to follow an explicit, ordered step-by-step procedure in which each step has a clear trigger and action. It wants to reach this with the least manual rewriting. What should you do?

1. Move the whole procedure into global instructions in the advanced agent application settings so that it is sent to the model on every conversational turn.
2. Split each paragraph of the procedure into its own sub-agent, and let the root agent pick the right sub-agent for each turn.
3. Use Restructure instructions to convert the prose into the recommended XML structure with constraints and a taskflow of trigger and action steps.
4. Add a constraint at the top of the instructions telling the model to think step by step before every answer.

Question 4, 1.2 Connecting enterprise data to Gemini Enterprise

A law firm uses Okta for single sign-on and stores matter documents in SharePoint Online, where Microsoft Entra ID groups control access. It wants Gemini Enterprise to search these documents in data ingestion mode, because search quality matters more to the firm than storage cost. Each attorney must see only the documents they are allowed to open in SharePoint. How should you configure identity for this data store?

1. Use Google Identity federated with Okta through SAML 2.0, and rely on the Okta groups that were synced to Google during the initial single sign-on setup.
2. Set up Workforce Identity Federation with Microsoft Entra ID, and use Entra ID groups to control document access.
3. Switch the SharePoint connector to data federation mode, so that users authenticate to SharePoint directly with OAuth.
4. Set up Workforce Identity Federation with Okta, and map google.subject to each user's Microsoft Entra ID object ID.

Question 5, 1.2 Connecting enterprise data to Gemini Enterprise

An aerospace supplier created a Gemini Enterprise unstructured data store a year ago from 40,000 PDF and DOCX maintenance manuals, using default settings without document chunking. The manuals are full of wiring diagrams and parts tables. A new RAG agent needs to retrieve relevant chunks, and answers must draw on image and table annotations. On the data store's Processing config tab, the team cannot select the layout parser. What should you do?

1. On the existing data store, add parser overrides for the pdf and docx file types that specify the layout parser, and re-import the manuals.
2. Create a new data store with layout-based document chunking and the layout parser turned on, and re-import the manuals into it.
3. Turn on document chunking on the existing data store's Processing config tab, then select the layout parser.
4. Turn on the OCR parser for PDFs on the existing data store with useNativeText set to true, and keep the store without chunking.