AI-102 Implement an agentic solution Practice Question
You are designing an agent in Microsoft Copilot Studio that must answer questions by using a large corpus of internal policy documents. The agent must provide accurate citations and must not invent policy details. You need to configure knowledge sources and grounding behaviour. Which two actions should you take? (Choose two.)
⚠ Common exam trap
The trap here is assuming that a more creative model produces better policy answers, when creativity increases the likelihood of unsupported details.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Configure the agent to use generative answers with the knowledge source and review the moderation settings.
Grounding the agent in the policy documents and enabling citations ensures answers trace back to authoritative content, while generative answers with reviewed moderation settings produce compliant responses. High creativity and reliance on pre-trained knowledge both increase the chance of fabricated policy details, and deferring accuracy to post-publication feedback does not meet the requirement.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Configure the agent to use generative answers with the knowledge source and review the moderation settings.
Why this is correct
Generative answers let the agent compose responses grounded in the configured knowledge source, which is how citations and accurate policy summarization are produced. Reviewing moderation settings ensures the generated content meets organizational standards for the policy domain. Together with a knowledge source, this is the supported way to deliver grounded, cited answers.
- ✗
Disable the knowledge source and rely on the model's pre-trained policy knowledge.
Why it's wrong here
Disabling the knowledge source removes grounding, so the agent answers from general model knowledge that cannot reflect your internal policies. This directly conflicts with the requirement to avoid invented details and to cite sources. Pre-trained knowledge is not a substitute for authoritative internal documents in a compliance-sensitive policy scenario.
- ✗
Publish the agent immediately and let user feedback correct inaccurate policy statements over time.
Why it's wrong here
Relying on user feedback to correct policy errors exposes users to inaccurate guidance and is not an acceptable control for compliance content. Grounding and citations should be in place before publishing. Feedback can help improve the agent later, but it does not satisfy the requirement that the agent not invent policy details.
- ✓
Add the policy documents as a knowledge source and enable citations in responses.
Why this is correct
Adding the documents as a knowledge source grounds the agent in authoritative content, and enabling citations makes the source of each answer visible. This combination supports accuracy and lets users verify answers against the original policy. Without a knowledge source, the agent would rely on model knowledge, which is exactly the behaviour that leads to invented policy details.
- ✗
Increase the agent's creativity level to high so it can paraphrase policies more naturally.
Why it's wrong here
High creativity increases variation in generated text, which raises the risk of fabricating details that are not in the source documents. For policy answers that must be exact and citable, lower creativity is preferable. This setting works against the requirement to avoid invented policy content and does not improve citation accuracy.
Go deeper
Related to this question
About these practice questions
This AI-102 question is part of Courseiva's 761-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam dumps. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Microsoft exam blueprint
This AI-102 practice question is part of Courseiva's free Microsoft certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AI-102 exam.