AI-102 Implement agentic AI solutions Practice Question
A bank is deploying an Azure AI Foundry agent that provides account balance information over the phone. The agent must authenticate callers by using voice biometrics before revealing any account details. The bank wants to integrate this authentication step into the agent's conversation flow without exposing sensitive data to the language model. Which approach should the bank use?
⚠ Common exam trap
The trap here is assuming the language model itself can perform biometric verification or that any authentication method, such as PIN, is acceptable when voice biometrics is explicitly required.
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
✓
Add a voice biometrics tool to the agent and configure a pre-action that runs before any account-related tool call.
The bank needs voice biometric authentication integrated into the agent flow without exposing sensitive data to the language model. A voice biometrics tool with a pre-action that gates account-related tool calls achieves this: the biometric check happens outside the model, and only a success token is passed to the orchestration layer, allowing account tools to run. This satisfies security and integration requirements.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Include the caller's voiceprint in the system message so the model can compare it to the live audio.
Why it's wrong here
Language models cannot process raw audio or perform biometric comparisons. Embedding a voiceprint in the system message would expose sensitive biometric data and is technically infeasible for the model. This approach also fails to provide a secure authentication gate, as the model cannot reliably verify identity from text.
- ✗
Use Azure Communication Services to record the call and send the audio to the agent as a text transcript for authentication.
Why it's wrong here
Transcribing audio to text loses the voice characteristics needed for biometric authentication. This method cannot verify the caller's identity and may introduce latency. It also does not integrate a dedicated authentication step into the agent's flow, so account details could still be revealed without proper verification.
- ✓
Add a voice biometrics tool to the agent and configure a pre-action that runs before any account-related tool call.
Why this is correct
Azure AI Foundry agents support tools and pre-actions that can enforce authentication before executing sensitive operations. A voice biometrics tool can verify the caller, and a pre-action ensures the verification runs before account tools are invoked. This keeps sensitive data out of the language model because the authentication result gates access to account information.
- ✗
Configure the agent to ask for the caller's account number and PIN, then validate them against a database before answering.
Why it's wrong here
This approach uses knowledge-based authentication rather than voice biometrics as required. It also exposes the account number and PIN to the language model if they are included in the conversation, which violates the requirement to keep sensitive data away from the model. The scenario explicitly requires voice biometrics, so this alternative does not meet the specification.
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.