AB-100 practice question 7 of 35

A global retailer is standardizing prompt guidance for agents used in Copilot Studio and Microsoft 365 across three business units. Data is regulated…

Full set: 708 questions
A global retailer is standardizing prompt guidance for agents used in Copilot Studio and Microsoft 365 across three business units. Data is regulated and must remain in-region, prompts must flow through dev/test/prod with approvals, and peak-hour latency must stay under 3 seconds. The team has inconsistent outputs because each unit writes prompts differently and some prompts encourage “best guess” answers when context is missing. Which three prompt engineering guidelines should be mandatory to meet consistency, governance, and reliability goals? (Select THREE.)
Answer options
A: Role-task-context-output template Correct answer
B: Inline citations with source timestamps
C: Self-critique chain-of-thought requirement
D: Tool-use policy with approval gates Correct answer
E: Prompt library versioned per environment Correct answer
F: Temperature increase for creativity and empathy
Correct Answer:
A. Role-task-context-output template; D. Tool-use policy with approval gates; E. Prompt library versioned per environment
Explanation

Microsoft’s prompt-engineering guidance for Copilot Studio and Microsoft 365 recommends: 1) a consistent role–task–context–output pattern to reduce variance, 2) explicitly governed tool invocation with approval gates to satisfy ALM and regulatory obligations, and 3) source-controlled, versioned prompt assets per dev/test/prod so every environment carries identical, approvable content and in-region storage. These three directly address consistency, governance/approvals, and reliability (≤3 s latency) without encouraging unsupported “best-guess” responses.

Why Incorrect

B. Citations are useful but not mandated for internal agents and do not solve governance or latency.
C. Self-critique chains add latency and may leak chain-of-thought, violating Microsoft guidance.
F. Higher temperature increases randomness, hurting consistency and reliability.

References

1. Microsoft Learn – “Engineering effective prompts for Microsoft Copilot” § Pattern (role-task-context-output).

2. Microsoft Power Platform ALM documentation – “Solutions and environments” § Version control of prompt assets.

3. Microsoft Responsible AI Standard

v2 § Input and tool governance – approval requirements.

4. Azure OpenAI latency guidance – <https://learn.microsoft.com/azure/ai-services/openai/concepts>.

Scroll to Top