AB-620 Microsoft Designing and Building Integrated AI Agent Solutions in Copilot Studio Free Practice Exam Questions (2026 Updated)

Comprehensive and Detailed Explanation From Microsoft AB-620 Study Guide: The Ask with Adaptive Card node is the interactive topic element that waits for a card submission and stores the user ' s responses as variables. The card must contain input controls with unique identifiers and an Action.Submit button so the host returns the collected values to Copilot Studio. A Message node can display a card, but it is not the correct choice when the topic must collect and bind structured input in one step. Action.Execute is not consistently supported across Copilot Studio channels; Microsoft documents host-specific schema limits, and the default web chat does not support that action. Using the latest schema indiscriminately can therefore break portability. The card should target the lowest schema version required by every intended channel, validate required fields, and provide clear labels and error messages. After submission, the topic variables should be typed and checked before they are passed to tools or flows. Testing is required in each production channel because rendering and supported Adaptive Card features differ between Teams, web chat, and customer-service hosts. Study Guide alignment: Plan and configure agent solutions > Configure topics > Configure adaptive cards; Manage variables.

===============

Requirement

Correct configuration

Users must be able to trace each answer back to its source.

Instruct the agent to cite sources in the knowledge settings.

The agent retrieves information from a centralized data index.

Configure Azure AI Search as the grounding data source.

Responses are generated by an enterprise-approved foundation model.

Deploy a model in Foundry to an agent and connect it to Copilot Studio.

Comprehensive and Detailed Explanation From [Microsoft AB-620 Study Guide]

Source citations provide traceability by connecting generated statements to the enterprise content used for grounding. Therefore, the agent’s knowledge instructions should require citations. For Azure AI Search, this also requires a usable URL in the search index. Copilot Studio interprets metadata_storage_path, or another field containing a complete URL, as the citation target. Consequently, instructions alone cannot produce functional links if the index does not expose a valid source URL.

Azure AI Search should be configured as the grounding source because it provides centralized, indexed retrieval for enterprise content. During a conversation, the user’s query is submitted to the configured search index, relevant passages are retrieved, and those passages become the grounding context for the generated response. Uploading documents directly to Copilot Studio would create a separate Dataverse-backed knowledge source and would bypass the required centralized index.

To satisfy organizational model governance, the approved foundation model must be deployed through Microsoft Foundry and associated with a Foundry agent that is connected to Copilot Studio. This ensures generation uses the approved model deployment rather than an unrelated default model.

Relevant study-guide area: Integrate and extend agents in Copilot Studio → Integrate agents with Azure → Configure generative answers by using Azure AI Search with Foundry . See Add Azure AI Search as a knowledge source and Connect to a Microsoft Foundry agent .