A consultant is enabling a new agentic AI capability in Dynamics 365 Sales that can autonomously draft and send follow-up emails to leads based on triggered events, such as a lead going quiet after an initial contact. Sales leadership is supportive of the time savings but is concerned about a generated email going out with inaccurate product claims or an inappropriate tone before anyone reviews it. What configuration should the consultant apply to address this concern while still capturing the automation benefit?
Select an answer to reveal the explanation.
Short Explanation
Leadership likes the idea of an assistant handling follow-up emails on its own, but the nervousness is understandable: nobody wants a bot firing off a message to a customer with the wrong facts or a tone that lands badly, and doing that automatically at scale is worse than a single human mistake. The way to keep the upside while covering that risk is simple: let the assistant draft the message however it wants, but put a person between the draft and the send button. That way the automation still saves the time of starting from a blank page, and a seller just has to skim and click send, or fix something first. Pulling the feature back to internal notes only kills the whole point of automating outreach. Cranking up how confident the system has to be before it acts doesn't actually check whether the content is correct or well-toned, it just changes when the system decides to act. And locking everything into one rigid template still leaves room for wrong details to get slotted in and mailed out untouched. Review before send is the piece that actually manages the risk.
Full Explanation
The correct answer is D. Requiring seller approval before an autonomously drafted email is sent inserts a human checkpoint that catches inaccurate claims or tone problems before they reach a customer, while still letting the agent do the drafting work that produces the time savings leadership wants to keep. Option A is incorrect because confining the agent to internal notes eliminates the customer-facing automation entirely, forfeiting the benefit the organization is trying to capture rather than managing the risk around it. Option B is incorrect because a high confidence threshold reflects the model's certainty about when to act, not the factual accuracy or tone of the generated content, so a confidently wrong or awkwardly worded email can still be produced and sent without review. Option C is incorrect because locking the agent to a single template constrains wording variety but does not prevent inaccurate dynamic content, such as incorrect product details or account references, from being inserted into that template and sent unreviewed.