A regional sales director notices that Copilot's deal-risk narratives on the forecast page never mention a recent contract-renewal clause type that historically correlates with slippage in this business unit. The director wants future narratives to weigh that clause type without disabling the built-in forecasting model. Which extension is appropriate?
Select an answer to reveal the explanation.
Short Explanation
When you want an AI-generated narrative to start caring about something new, the trick is to give it a clean, structured place to look, not to ask people to remember to mention it in passing. Adding a real field for the clause type and telling the narrative logic to weigh that field does exactly that, and it leaves the underlying forecasting model untouched, which is what was asked for. Turning the whole narrative feature off and writing summaries by hand throws out the automation completely, which is the opposite of extending it. Leaning on reps to type the clause type into a notes field is a gamble, because notes get skipped, worded inconsistently, or never read by the narrative logic in the first place. And building a separate chart that shows the clause type off to the side just gives the director one more screen to manually compare against the forecast page, rather than actually folding the signal into the narrative itself. Structured data feeding structured reasoning is the reliable path.
Full Explanation
The correct answer is C. Capturing the clause type as a structured custom field on the opportunity and referencing it in the agent's grounding instructions gives the narrative a reliable, queryable signal to weigh consistently, which is exactly what the director wants without touching the underlying forecasting model. Option A is incorrect because disabling the narrative feature and writing summaries by hand removes the automation entirely, contradicting the requirement to keep the built-in model running. Option B is incorrect because free-text notes are unstructured and inconsistently populated by reps, so Copilot may or may not surface the clause type depending on wording and whether it scans that note at all, which is not a dependable signal. Option D is incorrect because a separate Power BI report requires the director to manually cross-reference two different places instead of having the risk narrative itself account for the clause type, so it does not actually extend the narrative's reasoning. Structured grounding data is the only path that makes the signal consistently available to the narrative generation itself.