AB-100 practice question 27 of 35

A logistics company is rolling out a standard prompt guideline pack across dev/test/prod for multiple Copilot Studio agents. The environment is…

Full set: 708 questions
A logistics company is rolling out a standard prompt guideline pack across dev/test/prod for multiple Copilot Studio agents. The environment is regulated with approval gates for production changes, and you must demonstrate consistency without downtime during a weekend change window. Teams currently mix role instructions, formatting rules, and tool constraints in ad-hoc ways that cause inconsistent behavior. Steps 1. Define non-negotiable policies and refusal behaviors 2. Collect representative user journeys and constraints 3. Draft reusable prompt patterns and placeholders 4. Build an evaluation pack and regression checks What is the correct order of operations?
Answer options
A: 1 -> 3 -> 2 -> 4
B: 2 -> 3 -> 4 -> 1
C: 2 -> 1 -> 3 -> 4 Correct answer
D: 4 -> 2 -> 1 -> 3
Correct Answer:
C. 2 -> 1 -> 3 -> 4
Explanation

The correct sequence follows a standard, logical project lifecycle for developing a reliable AI system. The process must begin with understanding the user's needs and context (user journeys). Based on this understanding, foundational safety and governance rules (policies) are established. Only then can specific implementations (prompt patterns) be drafted. Finally, a robust evaluation and testing framework is built to ensure the prompts meet the requirements and policies consistently before deployment. This order minimizes rework and ensures requirements drive development.

Why Incorrect

A. Defining policies (1) before understanding user journeys (2) is premature; policies should be informed by the intended use cases to be effective and not overly restrictive.
B. Defining non-negotiable policies (1) as the final step is a major governance risk. Safety and refusal behaviors must be foundational, not an afterthought.
D. Building an evaluation pack (4) first is illogical. It is impossible to create meaningful tests without first defining the user journeys, policies, and prompts to be tested.

References

1. Microsoft. (2023). Overview of prompt engineering. Microsoft Learn. "The process of creating prompts is not a one-time task. It's an iterative process that involves... understanding the domain... designing and creating the prompt... testing and refining the prompt." This aligns with the sequence of understanding the use case (2)

designing (1

3)

and testing (4). Retrieved from https://learn.microsoft.com/en-us/azure/ai-services/prompt-engineering/overview (Section: Prompt engineering lifecycle).

2. Microsoft. (2024). Instructions and custom prompts in Copilot Studio. Microsoft Learn. "Start by identifying your business scenarios... Then

gather examples of both effective and ineffective conversations... Use these examples to craft instructions." This supports starting with user scenarios (2) before drafting instructions/prompts (3). Retrieved from https://learn.microsoft.com/en-us/microsoft-copilot-studio/nlu-authoring-prompts-instructions (Section: Get started).

Scroll to Top