A consultant configures Copilot for Sales account summaries for a distribution company. Two sellers view the summary for the same strategic account: one seller manages the account directly and has full read access to its opportunities and case records, while a second seller only has visibility into contact and account details due to a restrictive Dataverse security role. The second seller notices the AI-generated summary omits recent opportunity and case activity that appears in the first seller's summary. What is the most likely explanation for this difference?
Select an answer to reveal the explanation.
Short Explanation
Think of Copilot as a research assistant that can only read the files it's been let into the room to see. When it puts together an account summary for a seller, it isn't working from some universal master copy of the account, it's working from whatever opportunities, cases and notes that particular seller's security role lets them open. So if one seller has broad access and another has a narrower role that only covers contacts and the account record itself, the assistant handed to the narrower seller is going to come back with a thinner summary, not because it's broken or stale, but because it genuinely can't see the rest. The tempting traps here are assuming it's a caching delay, assuming summaries are identical for everyone by design, or assuming someone manually curated extra content for the better-informed seller. None of those hold up: the real driver is that the AI respects the same row and field level permissions the rest of the system already enforces. If you want richer summaries for a seller, the fix is adjusting what they're allowed to see, not troubleshooting the AI feature itself.
Full Explanation
The correct answer is B. Copilot for Sales generates account summaries by retrieving and grounding on records the requesting user is authorized to view in Dataverse, so a seller with a restrictive security role sees a summary limited to that role's visible opportunity and case data, while a seller with fuller access sees a richer summary drawn from the same account. Option A is incorrect because the summary difference here stems from access scope, not refresh timing; a caching explanation would produce inconsistent content for the same seller over time, not a consistent gap between two sellers' specific summaries. Option C is incorrect because summaries are not shared verbatim across users; generating per-user, permission-aware content is expected behavior, not evidence of a misconfiguration needing a reset. Option D is incorrect because summary content is drawn dynamically from records the seller can access rather than from content an admin manually pins to a timeline, so the gap is not explained by manual curation.