AI-102 Implement an agentic solution Practice Question
You are designing an agentic solution in Microsoft Foundry that uses a custom agent to answer questions about internal policies. The agent uses GPT-4o with retrieval augmented generation (RAG) on documents stored in Azure AI Search. Users report that the agent sometimes provides answers that contradict the retrieved documents. Which two actions should you take to improve response fidelity?
⚠ Common exam trap
Test-takers frequently think a simple system message (Option E) is sufficient to enforce grounding, but Microsoft tests that only the explicit 'strict grounding' parameter combined with source document limits provides reliable fidelity control in agentic solutions.
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
✓
Set the 'strict grounding' parameter to true and limit the number of source documents to 3.
Setting 'strict grounding' to true forces the model to rely exclusively on the provided source documents, and limiting the number of source documents to 3 reduces the chance of conflicting or irrelevant information being included. Option D is also correct because including the retrieved text directly in the prompt ensures the model has the exact context, and setting temperature to 0 makes the output deterministic, reducing hallucinations. Together, these actions improve response fidelity by enforcing strict grounding and reducing randomness.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Increase the temperature parameter to 0.9.
Why it's wrong here
Higher temperature increases creativity, not fidelity.
- ✗
Increase the chunk size in Azure AI Search to 2000 tokens.
Why it's wrong here
Chunk size optimization doesn't directly address contradictions.
- ✓
Set the 'strict grounding' parameter to true and limit the number of source documents to 3.
Why this is correct
Grounding and limiting sources reduces contradictions.
- ✓
Configure the agent to include the retrieved text in the prompt and set temperature to 0.
Why this is correct
Including retrieved text and low temperature improves fidelity.
- ✗
Add a system message instructing the model to only use provided context.
Why it's wrong here
System message alone is not sufficient.
Go deeper
Related to this question
About these practice questions
This AI-102 question is part of Courseiva's 945-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 by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
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.