Microsoft Updated AI-103 Exam Questions and Answers by husna

If/else condition expression: Not(IsBlank(Local.Var01))

Send message expression: {Upper(Local.Var01)}

The correct if/else condition is Not(IsBlank(Local.Var01)) because the workflow must continue only when the Ask a question node has captured a nonblank value. In Power Fx, IsBlank checks whether a value is blank, while Not reverses that Boolean result; therefore, Not(IsBlank(Local.Var01)) evaluates to true only when Var01 contains user input. IsEmpty(Local.Var01) is not the correct choice because IsEmpty checks whether a table contains records, not whether a text variable has a value. The Power Fx formula reference distinguishes these functions by defining IsBlank for blank values and IsEmpty for empty tables.

The Send message expression must be {Upper(Local.Var01)}. Microsoft Foundry workflow guidance uses the same pattern for an Ask a question node saved as Var01, followed by a Send message action that outputs {Upper(Local.Var01)}. The Local. prefix is required because the response is stored in a local workflow variable, and Upper() converts the stored text response to uppercase. Reference topics: Microsoft Foundry workflows, Power Fx expressions, local variables, if/else branching, and Send message actions.

The correct capability is token usage . In Microsoft Foundry observability, token consumption is the primary signal for diagnosing model-cost changes when request volume is unchanged. Token usage lets you distinguish whether costs increased because prompts became larger, retrieved or tool-provided context expanded, responses became longer, or agent execution added more model calls. Microsoft Foundry monitoring dashboards track operational metrics such as token consumption, latency, error rates, and quality scores, and the agent monitoring dashboard is specifically intended to help analyze token usage, latency, success rates, and evaluation outcomes for production traffic.

This directly matches the scenario because the issue is not more traffic, but changed request or response characteristics. Input tokens reveal whether the prompt, chat history, grounding data, or tool outputs being sent to the model increased. Output tokens reveal whether the model is generating longer completions. Expanded tool usage can also increase cost indirectly by adding more tool results, intermediate calls, and context into subsequent model requests; Foundry tracing and observability capture tool usage and token consumption for agent runs.

Evaluation metrics assess response quality and safety, not cost drivers. Latency identifies performance delays, and run success rate measures reliability. Reference topics: Microsoft Foundry observability, agent monitoring dashboard, token consumption, cost analysis, tool usage, and production monitoring.

The correct components are OpenTelemetry and Application Insights . Microsoft Foundry tracing for prompt agents is designed to capture detailed telemetry for agent execution, including latency, exceptions, prompt activity, and retrieval operations. For a Python service that invokes the agent outside the Foundry portal, OpenTelemetry is the appropriate instrumentation mechanism because the Foundry SDK tracing setup uses OpenTelemetry packages and Azure SDK tracing integration for client-side traces. This enables distributed tracing across the external Python service and the agent run.

Application Insights is the telemetry backend used by Foundry tracing. The Foundry tracing setup requires an Azure Monitor Application Insights resource to store traces, and traces can then be viewed in Foundry or directly in Azure Monitor Application Insights. Application Insights also provides performance and failure investigation experiences for response times, slow transactions, errors, and exceptions.

A Log Analytics workspace may underlie Application Insights data storage, but it is not the agent tracing component itself. The Azure Monitor Agent collects machine and guest telemetry, not application-level agent traces from a Python SDK invocation. Microsoft Sentinel is a security information and event management solution, not an end-to-end agent tracing mechanism. Reference topics: Microsoft Foundry tracing, Azure Monitor Application Insights, OpenTelemetry instrumentation, prompt agent observability, and Python SDK telemetry.

The correct recommendation is Azure AI Search. The case study states that the product detail sheets are stored as PDFs in storage1, and that Agent1 must be enabled to retrieve and use detailed product information from those sheets. It also specifies that the indexing pipeline must enable semantic and vector search, and that Agent1 must answer natural language questions about product details by using the product sheet information. Azure AI Search is the Azure service designed to ingest content from sources such as Azure Blob Storage, create searchable indexes, and support keyword, semantic, hybrid, and vector retrieval for Retrieval Augmented Generation (RAG) solutions.

Microsoft’s Azure AI Search guidance states that integrated vectorization can chunk content and generate embeddings during indexing, enabling vector search over source documents. It also states that Azure AI Search supports text and vector queries and can improve raw content for search-related scenarios through enrichment pipelines. Azure Translator is unrelated to retrieval. Document Intelligence can extract document structure, but it is not the retrieval index for Agent1. Grounding with Bing Search retrieves public web content, not Contoso’s private PDFs in storage1. Reference topics: Azure AI Search, RAG, semantic search, vector search, Azure Blob Storage indexing, and agent grounding.