A company plans to implement an automated process to retrieve and analyze customer feedback.

The solution requires an AI Builder prompt, a cloud flow, and a Dataverse table. The prompt performs the autonomous semantic analysis of each feedback item, including sentiment or other instructed classifications. The cloud flow supplies the event-driven orchestration: it retrieves new feedback, calls the prompt, interprets the result, writes the output, and branches to an escalation action when sentiment is negative. Dataverse provides persistent, queryable storage for the original feedback, model result, status, and reporting fields. A canvas app may be useful for reviewing results but is not required for autonomous execution. A business rule can validate or adjust Dataverse data but cannot independently call the generative model and orchestrate external escalation. The flow should include explicit failure handling, confidence or result validation, and an idempotent design so retries do not create duplicate escalations. Approved data policies must also permit the connectors used by the flow. The Study Guide covers “consume a prompt in cloud flows,” “configure cloud flow actions,” and the creation of Dataverse-backed business solutions. A, B, and E form the complete analysis, automation, and persistence architecture.

Study Guide reference/topic: “Create cloud flows; Create prompts and models in AI Hub.” AB-410 Study Guide | Microsoft Learn technical reference