Azure AI Apps and Agents Developer (AI-103) Exam Questions

Domain 1: Plan and Manage an Azure AI Solution (28%)

---

A company wants a single, unified platform to discover and deploy models from a large model catalog, build both simple declarative agents and full-code hosted agents, and get built-in tracing, evaluation, and governance for all of it. Which Microsoft platform is purpose-built for this?

⬜ Microsoft Foundry
⬜ Azure Kubernetes Service
⬜ Azure DevOps
⬜ Azure Data Factory

A developer wants to provision a single Azure resource that provides access to multiple AI capabilities at once (such as vision, language, and speech), using one endpoint and one set of keys, rather than provisioning and managing a separate resource for each capability. Which Azure resource type should be created?

⬜ A single-service resource
⬜ A multi-service resource
⬜ A resource group
⬜ A management group

An enterprise application calls an Azure AI Language endpoint from a backend service running on an Azure VM, and the security team wants to avoid storing and rotating a static API key in application configuration. Which authentication approach should be used instead?

⬜ Microsoft Entra ID authentication using a managed identity
⬜ Hardcoding the API key directly in source code
⬜ Sharing the API key over email with the development team
⬜ Disabling authentication on the resource

A company deploys a resume-screening AI model and later discovers it consistently ranks candidates from certain demographic groups lower, even when their qualifications are equivalent. Which Microsoft responsible AI principle is most directly violated?

⬜ Fairness
⬜ Transparency
⬜ Accountability
⬜ Privacy and security

A hospital deploying a diagnostic-support AI model wants to ensure the system performs consistently and safely under a wide range of real-world conditions, including unusual or edge-case patient data, and minimizes the risk of harmful errors. Which responsible AI principle does this concern primarily reflect?

⬜ Reliability and safety
⬜ Inclusiveness
⬜ Fairness
⬜ Transparency

A company building a customer-facing chatbot wants users to always be clearly informed that they are interacting with an AI system rather than a human agent, and wants the chatbot’s capabilities and limitations to be clearly documented for stakeholders. Which responsible AI principle does this practice support?

⬜ Transparency
⬜ Fairness
⬜ Privacy and security
⬜ Reliability and safety

A team building a generative AI chat application wants to automatically detect and block model outputs that fall into categories like hate speech, violence, self-harm, or sexual content, with configurable severity thresholds for each category. Which Microsoft Foundry capability provides this?

⬜ Content Safety / content filtering
⬜ Azure Resource Manager
⬜ Azure Cost Management
⬜ Microsoft Entra ID Conditional Access

A regulated financial services company wants to ensure that traffic to its Microsoft Foundry resource never traverses the public internet, restricting access to only its own private Azure virtual network. Which capability should it configure on the Foundry resource?

⬜ Private endpoint / virtual network isolation
⬜ A resource lock
⬜ A higher pricing tier
⬜ Multi-factor authentication for end users

A startup wants to try several AI capabilities during development at no cost before committing to a paid tier, understanding that this tier has significantly lower request limits than production tiers. Which type of pricing tier should they select when creating their Azure AI resource?

⬜ The Free (F0) tier
⬜ The Standard (S) tier
⬜ A Reserved Instance
⬜ A customer-managed key tier

An organization wants to browse a catalog of thousands of models from Microsoft, OpenAI, Anthropic, Meta, and other providers, compare their capabilities, and deploy the chosen model for their generative AI application, all from within one platform. Which Microsoft Foundry feature enables this?

⬜ The model catalog
⬜ Azure Policy
⬜ Azure Advisor
⬜ Resource tags

A team wants to grant a developer the ability to call models and use tools within a Foundry project, without giving them permission to delete the underlying Foundry resource or change its network configuration. Which Azure access control approach should be used?

⬜ Assign a scoped role-based access control (RBAC) role such as a Cognitive Services User role at the project level
⬜ Give the developer the Owner role on the entire Azure subscription
⬜ Share the resource’s primary API key with the entire team
⬜ Disable authentication so the developer can access it freely

A compliance team requires that data stored at rest in a company’s Foundry resource be encrypted using encryption keys that the company generates, controls, and can revoke itself, rather than relying solely on Microsoft-managed keys. Which capability should be configured?

⬜ Customer-managed keys (CMK)
⬜ A resource lock
⬜ A free-tier pricing plan
⬜ Multi-service resource consolidation

After deploying a generative AI application on Microsoft Foundry, an operations team wants to continuously collect logs and metrics about model calls, latency, and errors, and route them into Application Insights for long-term analysis and alerting. Which built-in Foundry capability supports this?

⬜ Observability and tracing (integrated with Application Insights)
⬜ Azure Blueprints
⬜ Custom Vision training
⬜ The Translator service

A data science team wants to organize the agents, model deployments, and connected data sources for one customer engagement separately from another engagement, while both engagements share the same underlying Foundry resource, quota, and networking configuration. Which Microsoft Foundry construct should be used to separate the two engagements’ work?

⬜ Foundry projects
⬜ Resource locks
⬜ Availability zones
⬜ Region pairs

A generative AI application’s default content filtering configuration is blocking some legitimate medical-education content because it is being flagged under the “self-harm” category at a low severity threshold. The team has a valid, approved use case and wants to adjust how aggressively that specific category is filtered for their deployment. What should they configure?

⬜ A custom content filter configuration with an adjusted severity threshold for that category, subject to Microsoft’s eligibility and review process
⬜ Permanently disable all content filtering for the resource with no review
⬜ Switch to a completely different, less capable model
⬜ Ignore the issue since content filters cannot be adjusted

A company deploying an internal generative AI assistant wants to make sure its data used for grounding (via RAG) stays isolated to their own tenant and is not used to train or improve Microsoft’s underlying foundation models. Which general principle from Microsoft’s approach to Foundry and Azure OpenAI addresses this concern?

⬜ Customer data used in Foundry (including RAG grounding data and prompts) is not used to train the underlying foundation models without explicit customer opt-in
⬜ All customer data is automatically pooled to improve the shared model for every tenant
⬜ Data isolation cannot be guaranteed on any Azure AI service
⬜ Customers must disable logging entirely to prevent any data use

A team designing a generative AI application follows Microsoft’s layered approach to responsible AI and wants to apply a mitigation at the “Safety System” level to help block harmful model output, independent of any application-level prompt engineering or user education. Which Microsoft Foundry capability operates at this safety system level?

⬜ Guardrails (formerly called content filters)
⬜ DALL-E model support
⬜ Fine-tuning
⬜ A resource lock

You are planning a Microsoft Foundry project that will contain multiple agents. Each agent will access the same Azure AI Search resource. You need to recommend a solution to centrally manage the Azure AI Search credentials within the project, so the same configuration is used across all the agents. What should you recommend?

⬜ Enable role-based access control (RBAC) for the Azure AI Search resource.
⬜ Add a connection to the Azure AI Search resource.
⬜ Disable key-based access control on the Azure AI Search resource.
⬜ Create a managed private endpoint that connects to the Azure AI Search resource.

Which statement best describes how keys, secrets, and endpoints work together in an Azure-based AI application?

⬜ The key is the location where model responses are stored, and the endpoint retrieves those responses from Azure Key Vault.
⬜ The endpoint stores sensitive values for an AI application, and the key determines how much data the endpoint can return.
⬜ The endpoint is a URL for calling a deployed model, and the key (stored as a secret in Azure Key Vault) authenticates the request made to that endpoint.
⬜ The secret is the model’s raw training data, and the endpoint encrypts it before storage in Azure Key Vault.

A startup with no prior AI experience wants to start building AI-powered applications and agents on Azure — including things like a document-understanding bot and a conversational support agent — without building model training infrastructure from scratch. Which Azure capability should they use as the foundation for this work?

⬜ Microsoft Paint
⬜ Azure AI services and related Azure AI tooling (Microsoft Foundry)
⬜ Windows Calculator
⬜ File Explorer

Which statement best describes a foundation model, such as those available in the Microsoft Foundry model catalog?

⬜ A small model trained from scratch by each customer solely on their own private data, with no general-purpose knowledge
⬜ A large model pretrained on broad data that can be used as-is or adapted (for example by fine-tuning) to many different downstream tasks
⬜ A rules-based system that has no training phase and only applies hard-coded if/else logic
⬜ A model that can only be used for a single, fixed task it was originally built for and cannot be adapted further

Domain 2: Implement Generative AI and Agentic Solutions (32%)

---

A developer deploys a GPT model in Microsoft Foundry and wants to establish the assistant’s persona, tone, and behavioral constraints (such as “always respond in formal English and never provide medical advice”) before any user messages are sent. Where should this instruction be placed in the chat completion request?

⬜ In the system message
⬜ In the user message
⬜ In the model’s fine-tuning dataset only
⬜ In the HTTP response headers

A developer wants a generative AI model to follow a specific output format (for example, always returning a JSON object with “name” and “summary” fields) and provides the model with two or three example input/output pairs directly in the prompt to demonstrate the desired pattern, without any model retraining. Which prompt engineering technique is this?

⬜ Few-shot prompting
⬜ Fine-tuning
⬜ Retrieval Augmented Generation (RAG)
⬜ Content filtering

A company wants its generative AI chatbot to answer questions using the company’s own internal, frequently updated product documentation, without retraining the underlying language model every time the documentation changes. Which architecture pattern is best suited to this requirement?

⬜ Retrieval Augmented Generation (RAG), grounding responses with a search index over the documentation
⬜ Increasing the model’s temperature parameter
⬜ Disabling the content filter
⬜ Switching to a smaller, cheaper model

A developer wants to build an AI agent by simply specifying its instructions, choosing a model from the catalog, and attaching a couple of built-in tools, all through the Foundry portal or SDK, without writing custom orchestration code or managing any infrastructure. Which Foundry agent-building approach fits this scenario?

⬜ A prompt agent
⬜ A hosted agent using a custom container
⬜ Fine-tuning a base model from scratch
⬜ Deploying a Kubernetes cluster

An agent built in Foundry Agent Service needs to look up a customer’s live order status from the company’s internal REST API during a conversation, something the underlying language model cannot know on its own. Which agent capability should be used to let the model invoke that external API during a conversation?

⬜ Tools / function calling
⬜ Increasing the max token limit
⬜ Enabling the free pricing tier
⬜ A resource lock

A team wants their Foundry agent to be able to write and execute a short Python snippet to perform a calculation or generate a chart as part of answering a user’s question, without the team writing custom code to sandbox and run that snippet themselves. Which built-in Foundry Agent Service tool provides this?

⬜ The code interpreter tool
⬜ The content filter
⬜ The pricing calculator
⬜ A management group

A company wants to build a complex workflow where a “router” agent analyzes an incoming customer request and delegates it to one of several specialized agents (billing, technical support, or returns), each with its own instructions and tools, and combines their outputs into a final response. What is this overall pattern called?

⬜ Multi-agent orchestration
⬜ Prompt engineering
⬜ Vector indexing
⬜ Resource tagging

A company has a very specific, narrow task (classifying support tickets into one of 12 internal categories using their own historical labeled examples) and wants the model itself to internalize this pattern so it performs the task accurately with short prompts and lower per-call token usage, rather than repeatedly including many examples in every prompt. Which approach best fits this requirement?

⬜ Fine-tuning a model on the company’s labeled dataset
⬜ Increasing the context window size only
⬜ Enabling multi-agent orchestration
⬜ Applying a resource lock

Before releasing a RAG-based chatbot to production, a team wants to systematically measure whether the chatbot’s answers are actually supported by the retrieved source documents (as opposed to being fabricated), using a repeatable, quantifiable process. Which Foundry capability addresses this?

⬜ Built-in evaluation metrics such as groundedness
⬜ Azure Cost Management budgets
⬜ Resource tags
⬜ Azure DNS

A developer sends a long conversation history along with a new user question to a deployed chat model, and receives an error indicating the request exceeds the model’s maximum input size. Which concept describes the limit that was exceeded?

⬜ The model’s context window (token limit)
⬜ The resource’s pricing tier
⬜ The content filter severity threshold
⬜ The region pair

A development team wants their Foundry agent to connect to an external, standardized tool server that exposes capabilities like file access and web search through a common, model-agnostic protocol, so the agent can use tools built by third parties without custom per-tool integration code. Which capability supports this?

⬜ Connecting to tools via the Model Context Protocol (MCP)
⬜ Applying a resource lock
⬜ Increasing the pricing tier
⬜ Enabling Availability Zones

A team wants full code-level control over their agent’s orchestration logic, including custom control flow between multiple tool calls and model invocations, and plans to use an open-source agent orchestration framework rather than the portal’s no-code agent builder. Which Foundry agent-building approach matches this need?

⬜ A hosted agent using a code-first framework such as Agent Framework, LangGraph, or Semantic Kernel
⬜ A prompt agent configured entirely in the portal
⬜ Increasing the content filter severity threshold
⬜ Applying a customer-managed key

A developer building a RAG-based generative AI application assembles the final prompt that gets sent to the generative model from several distinct parts. Which of the following are typically components of that assembled prompt? (Select all that apply.)

⬜ The retrieved data as context (grounding data)
⬜ The query
⬜ Instructions for the response, such as tone, length, and specificity
⬜ The vector embeddings

An AI agent is connected to the Azure Language MCP server as a tool provider. When processing a user’s prompt, how does the agent determine which specific Azure Language MCP tool to call?

⬜ The agent matches the prompt to the tool descriptions it receives from the MCP server
⬜ The developer writes custom routing logic to direct each prompt to a specific tool
⬜ The MCP server itself analyzes the prompt and automatically routes it to a tool
⬜ The user manually selects which tool should handle their prompt before sending it

What is the primary role of the Azure Language MCP server in an agentic AI solution?

⬜ To expose Azure Language’s text analysis capabilities — such as PII redaction, sentiment analysis, entity extraction, and summarization — as MCP tools that agents can call
⬜ To train and fine-tune custom language models for use by AI agents
⬜ To deploy and manage large language models within an Azure subscription
⬜ To provide a no-code portal for building declarative prompt agents

You have a Microsoft Foundry project that contains a high-traffic agent. After a recent update, operational costs increase significantly, even though monitoring confirms the volume of user traffic to the agent is unchanged. You suspect that changes to the request or response characteristics are causing the increase. You need to identify whether the additional costs are driven by the model input size, the model output size, or expanded tool usage. Which observability capability should you use?

⬜ Evaluation metrics
⬜ Token usage
⬜ Latency
⬜ Run success rate

What are the components of the prompt in a generative model using retrieval-augmented generation (RAG)? (Select all that apply.)

⬜ The retrieved data as context
⬜ The query
⬜ Instructions for the response, such as tone, length, and specificity
⬜ The vector embeddings

How does an agent determine which Azure AI Language MCP tool to call when processing a user’s prompt?

⬜ The developer writes routing logic to direct each prompt to a specific tool.
⬜ The agent matches the prompt to tool descriptions received from the MCP server.
⬜ The MCP server analyzes the prompt and automatically routes it to a tool.
⬜ The client randomly selects among all available tools.

What capability of Microsoft Foundry helps mitigate harmful content generation at the safety system level?

⬜ Fine-tuning
⬜ DALL-E model support
⬜ Guardrails and controls (content safety filtering)
⬜ Prompt flow orchestration

When constructing a prompt for a generative AI model in a retrieval-augmented application, which of the following is typically authored as part of the prompt itself, rather than produced internally by the retrieval system?

⬜ Instructions for the response, such as desired tone, length, and specificity
⬜ The vector embeddings computed for the retrieved documents
⬜ The similarity scores calculated between the query and indexed vectors
⬜ The index metadata describing how documents were chunked and embedded

A developer wants a generative AI model to return code in a specific programming language, following a particular structure, and respecting certain constraints (for example, no external libraries, under 50 lines). Which approach to writing the prompt is most effective?

⬜ Ask only for “code” with no further detail
⬜ Avoid describing the expected result and let the model infer everything
⬜ Include unrelated background text before the request
⬜ Specify the language, the task, any constraints, and the required output format

Domain 3: Implement Computer Vision Solutions (14%)

---

A marketing team wants to generate original promotional images from text descriptions (for example, “a minimalist product photo of a coffee mug on a wooden table”) as part of their generative AI application. Which type of model should be deployed for this capability?

⬜ An image generation model (such as a DALL-E-family model)
⬜ A speech-to-text model
⬜ A text embedding model
⬜ A key phrase extraction model

A media company wants to automatically generate a short natural-language caption describing the content of each uploaded photo (for example, “a dog running on a beach”), along with a list of relevant tags. Which Azure Vision capability should they use?

⬜ Image Analysis (captioning and tagging)
⬜ Custom Vision object detection
⬜ Document Intelligence
⬜ Translator

A manufacturer wants to train a model that can tell the difference between three specific types of proprietary machine parts in photos taken on their factory floor, a distinction that no general-purpose, prebuilt vision model would know out of the box. Which Azure service is designed for training this kind of custom image classification model using the company’s own labeled images?

⬜ Custom Vision
⬜ Azure Vision Image Analysis
⬜ Face service
⬜ Video Indexer

In addition to classifying what is in an image overall, a retailer wants a model that can also draw bounding boxes around each individual product on a store shelf and identify the location of each one in the photo. Which Custom Vision project type should be created?

⬜ Object detection
⬜ Image classification
⬜ Sentiment analysis
⬜ Key phrase extraction

An access-control vendor wants to build a solution that can detect the presence and location of human faces in a video feed and analyze attributes for legitimate, approved access-control scenarios, in compliance with Microsoft’s Limited Access policies governing facial recognition. Which Azure Vision capability is relevant here?

⬜ The Face service
⬜ Custom Vision image classification
⬜ Translator
⬜ Question answering

A media company has a large archive of video files and wants to automatically extract insights such as spoken transcripts, detected faces, keywords, and scene changes from each video, without manually reviewing the footage. Which Azure AI capability is purpose-built for extracting these combined insights from video content?

⬜ Azure AI Video Indexer
⬜ Custom Vision object detection
⬜ Document Intelligence
⬜ Key phrase extraction on transcripts only

A quality-control application on a manufacturing line needs to identify whether a product on the assembly line is a specific one of five known defect types, using photos captured by a fixed camera, and the categories are mutually exclusive (a product has exactly one defect type or none). Which Custom Vision project type is the best fit?

⬜ Image classification (multiclass)
⬜ Object detection
⬜ OCR
⬜ Video Indexer

You are deploying a support agent that enables users to upload photos. You need to automatically classify uploaded images for harmful content, and the solution must block content based on severity levels. What should you do?

⬜ Implement image moderation.
⬜ Enable prompt shields.
⬜ Apply keyword scanning to optical character recognition (OCR) output by using Azure Vision in Foundry Tools.
⬜ Use blocklists.

Domain 4: Implement Text Analysis Solutions (14%)

---

A retail company wants to automatically determine whether each customer product review expresses a positive, negative, mixed, or neutral opinion, and also identify which specific aspects of the product (like “battery life” or “screen quality”) drove that opinion. Which Azure Language capability should be used?

⬜ Sentiment analysis and opinion mining
⬜ Key phrase extraction
⬜ Language detection
⬜ Named entity recognition

A news aggregation service wants to automatically pull out the most important topics and concepts from each article (such as “climate policy,” “renewable energy,” and “carbon tax”) to use as article tags, without extracting full sentences. Which Azure Language capability fits this need?

⬜ Key phrase extraction
⬜ Sentiment analysis
⬜ PII detection
⬜ Custom question answering

A healthcare provider needs to automatically identify and redact sensitive personal details — such as patient names, phone numbers, and social security numbers — from free-text clinical notes before sharing them with a research partner. Which Azure Language capability is designed for this?

⬜ PII (Personally Identifiable Information) detection
⬜ Custom Vision object detection
⬜ Translator
⬜ Video Indexer

A customer support bot needs to determine what a user is trying to accomplish from a free-text message (for example, recognizing the intent “CheckOrderStatus” and extracting the entity “order number: 12345”) so it can route the request to the right backend workflow. Which Azure Language capability is purpose-built for this intent-and-entity extraction task?

⬜ Conversational Language Understanding (CLU)
⬜ Sentiment analysis
⬜ OCR
⬜ Video Indexer

An enterprise wants to build a FAQ bot that answers employee questions by matching them against a curated set of question-and-answer pairs drawn from HR policy documents, returning the best matching pre-written answer rather than generating a new response. Which Azure Language capability is designed for this?

⬜ Custom question answering (CQA)
⬜ Named entity recognition
⬜ Key phrase extraction
⬜ Custom Vision

A global e-commerce platform wants to automatically translate product descriptions from English into a dozen other languages for its international storefronts, preserving formatting where possible. Which Azure AI service should be used?

⬜ Azure Translator
⬜ Azure Language sentiment analysis
⬜ Azure Vision OCR
⬜ Custom question answering

A content moderation system ingests text from many countries and first needs to automatically determine which language each piece of text is written in before routing it to the correct language-specific downstream analysis pipeline. Which Azure Language capability accomplishes this first step?

⬜ Language detection
⬜ Sentiment analysis
⬜ Key phrase extraction
⬜ PII detection

You are creating an agent workflow in a Microsoft Foundry project to support natural voice interactions. The agent must receive continuous audio input, convert the input into text for reasoning, and then return spoken responses to a user. The workflow must support turn-taking dynamics, where the agent begins to generate speech output before the user finishes speaking, and must operate with low latency to maintain a conversational experience. You need to enable both speech to text and text to speech in a real-time agent interaction. What should you do?

⬜ Use an embeddings model to encode the audio, and then decode the audio into text and speech.
⬜ Use batch transcription to convert the audio input and return text responses from the agent.
⬜ Use speech translation to convert the audio into another language and return the translated text.
⬜ Use real-time speech to text for incoming audio and text to speech for agent responses.

A developer writes code that creates a TextAnalyticsClient object, supplying it with the resource’s endpoint and an AzureKeyCredential, and then calls methods on that object to analyze sentiment and extract key phrases from text. What is the purpose of this client object in the Azure Language SDK?

⬜ It stores UI settings for the application
⬜ It helps application code communicate with the Azure Language service
⬜ It stores the text to be analyzed
⬜ It renders the analysis results in a user interface

Domain 5: Implement Information Extraction Solutions (12%)

---

In a Retrieval Augmented Generation (RAG) pipeline, documents and user queries are converted into high-dimensional numerical representations so that semantically similar pieces of text can be found even when they don’t share exact keywords. What are these numerical representations called?

⬜ Embeddings
⬜ Tokens
⬜ Resource tags
⬜ System messages

A logistics company wants to extract all the printed and handwritten text from scanned shipping labels and warehouse documents so it can be indexed and searched. Which Azure Vision capability is designed specifically for this text-extraction task?

⬜ OCR (Optical Character Recognition / Read API)
⬜ Face detection
⬜ Image captioning
⬜ Spatial analysis

An accounts payable team receives thousands of vendor invoices in varying layouts and wants to automatically extract standard fields (vendor name, invoice number, total amount, due date) without training any custom model, since invoices are a well-known, common document type. Which Azure AI capability should they use?

⬜ A prebuilt Document Intelligence model (such as the invoice model)
⬜ Custom Vision object detection
⬜ Conversational Language Understanding
⬜ Video Indexer

A logistics company uses a proprietary bill-of-lading form with a unique layout not covered by any of Document Intelligence’s prebuilt models, and wants to extract specific custom fields consistently from this form. What should they do?

⬜ Train a custom Document Intelligence model using labeled examples of their own form
⬜ Use the prebuilt invoice model as-is without modification
⬜ Use Custom Vision image classification instead
⬜ Use the Translator service to reformat the document

A company wants Azure AI Search to automatically pull new and updated documents from an Azure Blob Storage container on a recurring schedule and add them to a search index, without writing custom code to push each document into the index manually. Which Azure AI Search component enables this automatic, scheduled data pull?

⬜ An indexer
⬜ A skillset
⬜ A knowledge store
⬜ A vector index only

While indexing a large set of scanned PDF contracts, a company wants Azure AI Search to automatically run OCR to extract text from the scanned images, detect and redact personal information, and extract key phrases, all as part of the indexing pipeline, before the content lands in the search index. Which Azure AI Search feature orchestrates this chain of AI processing steps?

⬜ A skillset (AI enrichment pipeline)
⬜ A resource lock
⬜ A management group
⬜ A region pair

A knowledge mining solution needs to find documents that are conceptually similar to a user’s query even when the query uses completely different wording than the source documents (for example, matching “car won’t start” to a document about “vehicle fails to power on”). Plain keyword search alone would miss this match. Which Azure AI Search capability should be enabled to support this kind of conceptual matching?

⬜ Vector search (using embeddings)
⬜ A resource lock
⬜ OCR skill only
⬜ Multi-service resource consolidation

During the AI enrichment process for a set of customer support transcripts, a company wants to detect and mask any personal information (such as phone numbers or email addresses) that appears in the transcripts, as one of the automated steps in the same pipeline that also extracts key phrases and runs OCR. Which Azure AI Search skill should be added to the skillset for this specific requirement?

⬜ The PII detection skill
⬜ The image analysis skill
⬜ The language detection skill only
⬜ The custom entity lookup skill only

You have a chat app in a Microsoft Foundry project and an Azure AI Search vectorized index. You need to connect to the index to meet the following requirements: complex questions must retrieve information from multiple chunks; multi-turn conversations must influence retrieval planning; and retrievals must run in parallel to reduce latency. Which retrieval approach should you use?

⬜ Classic Retrieval Augmented Generation (RAG)
⬜ Chain of thought
⬜ Agentic Retrieval Augmented Generation (RAG)
⬜ Iterative retrieval