The answer is to configure the agent to include the retrieved text in the prompt and set the temperature parameter to 0. Including the retrieved text directly in the prompt grounds the model’s response in the actual source documents, which is the core technique for improving RAG response fidelity and reducing hallucinations—the model cannot contradict what it can explicitly read. Setting temperature to 0 minimizes randomness, forcing the model to choose the most probable, deterministic output based strictly on that grounded context. On the AI-102 exam, this question tests your understanding of how to control generative AI behavior within agentic solutions in Microsoft Foundry, specifically the balance between creativity and factual adherence. A common trap is assuming a system message alone can enforce fidelity, but without explicit document grounding and zero randomness, the model will still fabricate. Memory tip: “Ground and freeze”—ground the prompt with retrieved text, then freeze creativity by setting temperature to zero.
AI-102 Implement an agentic solution Practice Question
This AI-102 practice question tests your understanding of implement an agentic solution. Match the stated requirement to the specific cloud service, access model, or configuration option — many options are valid in isolation but not for this scenario. After answering, compare your reasoning against the explanation and wrong-answer breakdown below. Once you have made your selection, read the full explanation to reinforce the concept and understand why each distractor is designed to mislead on exam day.
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?
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.
Option D is correct because grounding with retrieved documents reduces hallucination. Option B is correct because limiting source documents reduces noise. Option A is wrong because increasing temperature increases randomness. Option C is wrong because system message alone doesn't guarantee fidelity. Option E is wrong because chunk size optimization is about performance, not contradiction.
Key principle: NAT direction and interface roles matter as much as the IP address mapping. Inside/outside designation controls which traffic is translated.
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.
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.
Related concept
Static NAT maps one inside address to one outside address.
✓
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.
Related concept
Static NAT maps one inside address to one outside address.
✗
Add a system message instructing the model to only use provided context.
Why it's wrong here
System message alone is not sufficient.
Common exam traps
Common exam trap: NAT rules depend on direction and matching traffic
NAT is not only about the public address. The inside/outside interface roles and the ACL or rule that matches traffic are just as important.
Detailed technical explanation
How to think about this question
NAT questions usually test address translation, overload/PAT behaviour, static mappings and whether the right traffic is being translated. Read the interface direction and address terms carefully.
KKey Concepts to Remember
Static NAT maps one inside address to one outside address.
PAT allows many inside hosts to share one public address using ports.
Inside local and inside global describe the private and translated addresses.
NAT ACLs identify traffic for translation, not always security filtering.
TExam Day Tips
→Identify inside and outside interfaces first.
→Check whether the scenario needs static NAT, dynamic NAT or PAT.
→Do not confuse NAT matching ACLs with normal packet-filtering intent.
Key takeaway
NAT direction and interface roles matter as much as the IP address mapping. Inside/outside designation controls which traffic is translated.
Real-world example
How this comes up in practice
A cloud solutions architect for a retail company is evaluating services for a new workload. The correct answer here reflects best practice for the specific scenario described — not a general cloud recommendation. NAT direction and interface roles matter as much as the IP address mapping. Inside/outside designation controls which traffic is translated. Cloud exam questions reward reading the constraint carefully: the same technology can be right or wrong depending on the use case.
What to study next
Got this wrong? Here's your next step.
Review the four NAT address types (inside local, inside global, outside local, outside global), PAT port overload, and static vs dynamic NAT use cases. Then practise related AI-102 NAT questions on configuration and troubleshooting.
Implement an agentic solution — This question tests Implement an agentic solution — Static NAT maps one inside address to one outside address..
What is the correct answer to this question?
The correct answer is: Set the 'strict grounding' parameter to true and limit the number of source documents to 3. — Option D is correct because grounding with retrieved documents reduces hallucination. Option B is correct because limiting source documents reduces noise. Option A is wrong because increasing temperature increases randomness. Option C is wrong because system message alone doesn't guarantee fidelity. Option E is wrong because chunk size optimization is about performance, not contradiction.
What should I do if I get this AI-102 question wrong?
Review the four NAT address types (inside local, inside global, outside local, outside global), PAT port overload, and static vs dynamic NAT use cases. Then practise related AI-102 NAT questions on configuration and troubleshooting.
What is the key concept behind this question?
Static NAT maps one inside address to one outside address.
About these practice questions
Courseiva creates original exam-style practice questions with explanations and wrong-answer analysis. It does not publish real exam questions, exam dumps, or protected exam content. Learn why practice questions differ from exam dumps →
Share a tip, memory trick, or ask about the reasoning behind this question. Do not post real exam questions, leaked content, braindumps, or copyrighted exam material. Comments are moderated and may be removed without notice.
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.
Question Discussion
Share a tip, memory trick, or ask about the reasoning behind this question. Do not post real exam questions, leaked content, braindumps, or copyrighted exam material. Comments are moderated and may be removed without notice.
Sign in to join the discussion.