AI-102 Implement an agentic solution Practice Question
You are building an agentic solution using Microsoft Semantic Kernel. The agent uses a planner to orchestrate multiple functions. You want to improve the planner's ability to handle complex user requests that involve multiple steps. Which THREE strategies should you implement?
⚠ Common exam trap
Microsoft often tests the misconception that reducing function count (Option A) or using simpler prompts (Option D) improves planning, when in fact these strategies limit the planner's expressiveness and ability to handle complex, multi-step requests.
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
✓
Enable the planner to ask the user for clarification when the request is ambiguous
Option B is correct because allowing the planner to ask the user for clarification when a request is ambiguous prevents it from guessing at missing parameters or intent, which is essential for correctly decomposing complex multi-step requests. Option C is correct because composite functions encapsulate common multi-step sub-tasks into a single callable unit, reducing the planner's reasoning burden and making orchestration of complex workflows more reliable. Option E is correct because few-shot examples of multi-step workflows in the planner prompt demonstrate the expected decomposition and sequencing pattern, improving the planner's ability to generate correct multi-step plans. Option A is not appropriate because arbitrarily limiting available functions removes capabilities the agent needs for complex requests rather than improving planning quality. Option D is not appropriate because a simple, generic prompt provides no guidance on multi-step decomposition and would degrade, not improve, planning performance for complex tasks.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Limit the number of available functions to reduce planning overhead
Why it's wrong here
Restricting the function pool shrinks what the planner can compose, so multi-step requests needing those functions cannot be fulfilled at all. It is tempting because trimming tools genuinely reduces token usage and mis-selection in narrow, single-domain agents where the function set already covers every required capability.
- ✓
Enable the planner to ask the user for clarification when the request is ambiguous
Why this is correct
Clarification prompting lets the planner resolve ambiguous intent before committing to a function sequence, preventing mis-ordered or missing steps in multi-step orchestration. This directly satisfies the stem's goal of handling complex, multi-step requests, since ambiguity is a primary cause of planner failure in Semantic Kernel pipelines.
- ✓
Create composite functions that encapsulate common multi-step sub-tasks
Why this is correct
Composite functions bundle recurring multi-step sub-tasks into a single callable unit, so the planner reasons over fewer, higher-level steps rather than orchestrating every primitive function individually. This directly reduces planning complexity for multi-step requests, satisfying the stem's goal of improving the planner's handling of complex, multi-step user requests.
- ✗
Use a simple, generic prompt to avoid overfitting
Why it's wrong here
A generic prompt gives the planner no function descriptions or task decomposition guidance, so it cannot reliably chain multi-step calls. It is tempting because generic prompts reduce overfitting in some machine-learning contexts, and would be the right approach when training a model on broad data rather than orchestrating functions.
- ✓
Provide few-shot examples of multi-step workflows in the planner prompt
Why this is correct
Few-shot examples demonstrate the exact multi-step workflow patterns the planner must imitate, grounding its function selection and sequencing in concrete demonstrations rather than abstract instructions. This directly addresses the stem's constraint of handling complex multi-step requests, improving orchestration accuracy within Microsoft Semantic Kernel's planner prompt.
Go deeper
Related to this question
About these practice questions
One of 761 original AI-102 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. 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.