AI-102 Implement an agentic solution Practice Question
You are implementing an agent with Azure AI Agent Service that must run a multi-step task: retrieve a customer record, then create a support ticket containing that record. You want the agent to complete both steps in a single run and to be able to report intermediate progress. Which two capabilities should you rely on? (Choose two.)
⚠ Common exam trap
Candidates often confuse retrieval-augmented features such as embeddings or file search with the action-execution and observability features that actually drive a multi-step agent run.
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
✓
Tool calling, so the model can request the retrieval and ticket-creation functions during the run.
Tool calling lets the model request the customer lookup and the ticket creation as part of one run, while run steps give the application visibility into each invocation and result. Together they enable a single multi-step run with observable progress, which is exactly what the scenario requires.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
File search over the support policy documents, so the agent can justify the ticket priority.
Why it's wrong here
File search is a retrieval tool for document content and has no bearing on executing the retrieval and ticket-creation calls in sequence. It might inform how the agent phrases a priority, but it does not enable the two required actions or progress reporting. The scenario's steps are API actions, not policy lookups.
- ✓
Tool calling, so the model can request the retrieval and ticket-creation functions during the run.
Why this is correct
Tool calling is how an agent takes actions in Azure AI Agent Service. The model emits a tool call, the service or your code executes it, and the result returns to the model so it can decide the next step. Without tool calling, the agent could only produce text and could not retrieve the customer record or create the ticket.
- ✓
Run steps, so the application can observe each tool call and its result as the run progresses.
Why this is correct
Run steps expose the ordered events of a run, including tool invocations, their inputs and outputs, and message creation. Polling run steps is what lets your application surface intermediate progress such as 'customer retrieved' before the ticket is created, and it is also the primary diagnostic surface when a run stalls.
- ✗
Vector embeddings of the ticket schema, so the model can match the customer record to the correct ticket fields.
Why it's wrong here
Embeddings support semantic search over unstructured content; they do not drive structured function invocation or field mapping. The ticket fields are described by the function's JSON schema, and the model fills arguments according to that schema. Adding embeddings would not enable multi-step execution and would add an unnecessary indexing dependency.
- ✗
A separate thread per step, so each tool call is isolated from the others.
Why it's wrong here
Threads hold conversation state across messages and runs. Splitting the two steps into separate threads would discard the context from the retrieval before the ticket is created, forcing you to copy data manually. A single thread with multiple run steps is what preserves continuity within one multi-step task.
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 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.