Courseiva
Implement Generative AI And Agentic SolutionshardMultiple SelectObjective-mapped

AI-103 Implement Generative AI And Agentic Solutions Practice Question

You are building an autonomous agentic workflow using Microsoft Foundry and Semantic Kernel. You need to ensure the agent operates safely and adheres to human oversight requirements. Which THREE design patterns should you apply? (Choose three.)

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

Implement human-in-the-loop approval gates before the agent executes high-impact tool actions such as database updates or financial transactions.

Human-in-the-loop approval gates, transaction boundaries, and rate limiting ensure safe agentic execution.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

  • Grant the agent root-level administrative access to all cloud infrastructure services.

    Why it's wrong here

    Granting root access violates the principle of least privilege and introduces extreme security risks.

  • Implement human-in-the-loop approval gates before the agent executes high-impact tool actions such as database updates or financial transactions.

    Why this is correct

    Human approval gates prevent autonomous execution of destructive or sensitive actions.

  • Configure strict idempotency keys for external tool calls to prevent duplicate actions if retried.

    Why this is correct

    Idempotency ensures safe retries without executing duplicate side effects.

  • Implement circuit breakers to halt agent execution if error rates or token consumption spike abnormally.

    Why this is correct

    Circuit breakers protect against cascading failures and runaway agent behavior.

  • Allow the agent unlimited recursive tool execution without loop detection.

    Why it's wrong here

    Unlimited recursion leads to infinite loops and runaway costs.

About these practice questions

Courseiva writes every AI-103 question from scratch — 510 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. Learn why practice questions differ from exam dumps →

How Courseiva writes practice questions · Editorial policy

JA

Written and reviewed by Johnson Ajibi, MSc IT Security

Senior Network & Security Engineer · founder of Courseiva

Last reviewed August 2026 · checked against the official Microsoft exam blueprint

This AI-103 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-103 exam.