Welcome to awslagi.com – Sharing AWS, Google Cloud, Microsoft Azure IT Exams. It's free for all!

AI-103: Developing AI Apps and Agents on Azure

Master the Microsoft Developing AI Apps and Agents on Azure (AI-103) certification exam with 54 realistic practice questions covering Implement generative AI and agentic solutions, Implement text analysis solutions, Plan and manage an Azure AI solution, Implement information extraction solutions.

4.8★★★★★(175 ratings)
12,721 studentsIntermediate
Prepare for the Microsoft Developing AI Apps and Agents on Azure (AI-103) certification with scenario-based practice questions modeled on real exam objectives. You will build practical confidence across key domains including Implement generative AI and agentic solutions, Implement text analysis solutions, Plan and manage an Azure AI solution, Implement information extraction solutions. Each question includes structured answer options and hint answers to help you identify knowledge gaps quickly, reinforce core Microsoft concepts, and pass the AI-103 exam on your first attempt.

What you'll learn

  • Implement generative AI and agentic solutions
  • Implement text analysis solutions
  • Plan and manage an Azure AI solution
  • Implement information extraction solutions
  • Implement computer vision solutions

AI-103

Lectures1
Questions51
Duration30 week
Students12,721

$20.00

Full Free Question Bank (51 Questions)

AI-103: Developing AI Apps and Agents on Azure (AI-103) Practice Questions & Verified Answers

Click any option to test your knowledge, or reveal the verified answer and detailed explanation below each question.

Question #1Part 1Implement text analysis solutions

You have an application named App1 that uses Azure Speech in Foundry Tools to transcribe live calls. Transcript segments frequently contain both English and Spanish. App1 sends each segment to Azure Translator in Foundry Tools for translation into another language, but mixed-language segments sometimes produce incomplete or incorrect translations. You need to reduce translation errors, ensuring that the entire transcript is translated successfully. What should you do before sending the segments to Translator?

AUse document translation to translate the entire transcript as a single document.
BSplit the mixed-language segments into single-language segments and translate each segment separately.
CEnable automatic language detection for the translation request.
DSpecify English as the source language in the translation request for all the segments.
Question #2Part 1Implement generative AI and agentic solutions

You have a Microsoft Foundry project named Project1 that contains an agent, and the agent uses an OpenAPI 3.0 specification to call an external weather service. The weather service requires a key that must be passed in an HTTP header, and the key value is stored as a connection in Project1. You need to ensure that the key value from the connection is automatically included whenever the OpenAPI tool is invoked. What should you configure in the OpenAPI specification?

Aa header parameter defined for each operation
Ban Azure Key Vault connection
Can API key security scheme
Da Bearer token security scheme
Question #3Part 1Implement generative AI and agentic solutions

You have a Microsoft Foundry project named Project1 that contains the following: - An OpenAPI tool that calls an external API - A project connection named Connection1 that stores the API key for the external API When an agent calls the OpenAPI tool, the API returns a 401 Unauthorized error, and traces show that the API key header is not being sent. You need to ensure that the OpenAPI tool automatically includes the API key from Connection1 on every request. What should you do?

AEnable identity passthrough so that the tool uses the Microsoft Entra token of the caller.
BAdd the API key header manually to the OpenAPI specification.
CConfigure the tool to use the default connection of Project1.
DConnect the tool to Connection1.
Question #4Part 1Implement generative AI and agentic solutions

You have a Microsoft Foundry project that contains an agent, and the agent uses Azure Speech in Foundry Tools. You fine-tune a baseline speech-to-text model for the en-US locale and publish it. When the agent calls the Speech to text REST API, it returns an error indicating that the project ID is invalid. You need to set the project property to the correct value. What should you set the project property to?

Athe project URL
Bthe custom speech project ID
Cthe project ID
Dthe custom speech endpoint URL
Question #5Part 1Implement text analysis solutions

You are building a speech processing solution in Microsoft Foundry for a customer support platform. The platform will transcribe live phone calls so that supervisors at your company can view the call transcripts and detect issues while calls are still in progress. The call audio arrives as a continuous stream from the telephony system. You need the call transcripts to appear within only a few seconds of the audio stream. What should you do?

AUse text to speech by using a custom neural voice.
BUse speech translation to generate the transcripts into multiple languages.
CRun a batch transcription job on recorded audio files.
DUse real-time speech to text to process streaming audio input.
Question #6Part 1Implement generative AI and agentic solutions

You have a Microsoft Foundry project that contains an agent, and the agent has a Model Context Protocol (MCP) tool that queries a knowledge base stored in Azure AI Search. Some agent runs return answers straight from the base model without invoking the knowledge base, so those responses lack grounded citations. You are given the following code snippet, which runs the agent: ![Question Image](https://cdn.examcademy.com/images/questions/1783676238651-7e94yywb.png) You need to add the correct `tool_choice` parameter to the code so that the agent is deterministically forced to invoke the MCP tool on every run. What should you add?

Atool_choice={“required”}
Btool_choice={“auto”}
Ctool_choice={“type”:“knowledge_base”}
Dtool_choice ={“type”:“mcp”}
Question #7Part 1Implement generative AI and agentic solutions

You have a Microsoft Foundry project. You are planning a customer support solution built around an agent. The solution must: - Provide accurate, context-aware responses grounded in internal product documentation stored in Azure AI Search. - Require deep, multi-step reasoning across long contexts. - Generate detailed natural language responses. Which type of model should you use to power the agent?

Aa multimodal model
Ba small language model (SLM)
Ca key phrase extraction model
Da large language model (LLM)
Question #8Part 1Implement information extraction solutions

You have a Microsoft Foundry project that contains an agent. The agent ingests scanned PDF vendor invoices that contain tables and embedded QR codes. The agent must preserve the PDF layout in the extracted output so that downstream processing can reference sections and tables. You plan to call Azure Content Understanding in Foundry Tools. You need to extract the content and layout elements and detect the QR codes, without requiring a language model deployment. Which built-in analyzer should you use?

Aprebuilt-documentFieldSchema
Bprebuilt-read
Cprebuilt-documentSearch
Dprebuilt-layout
Question #9Part 1Implement computer vision solutions

You are deploying a support agent that lets users upload photos. You need to automatically classify the uploaded images for harmful content. The solution must block content according to severity levels. What should you do?

AApply keyword scanning to optical character recognition (OCR) output by using Azure Vision in Foundry Tools.
BEnable prompt shields.
CUse blocklists.
DImplement image moderation.
Question #10Part 1Implement generative AI and agentic solutions

Solution: You increase the value of themax_tokensparameter. Does this solution meet the goal?

AYes
BNo
Question #11Part 1Implement generative AI and agentic solutions

Solution: You add a reflection pass that regenerates the response if the required clauses are missing. Does this solution meet the goal?

AYes
BNo
Question #12Part 1Implement generative AI and agentic solutions

Solution: You increase the value of thetemperatureparameter. Does this solution meet the goal?

AYes
BNo
Question #13Part 1Implement generative AI and agentic solutions

Solution: You run an evaluation flow that scores responses for completeness and blocks any response that falls below a defined threshold. Does this solution meet the goal?

AYes
BNo
Question #14Part 1Implement generative AI and agentic solutions

You have a customer support agent built with the Microsoft Foundry Agent Service. The agent calls an Azure OpenAI model deployment. During load testing, calls intermittently fail with an HTTP 429 "rate limit exceeded" error. You need to handle the throttling to reduce call failures and improve reliability under load. The solution must stay within the service and model limits. What should you do?

ACreate a new thread and retry the calls immediately.
BReduce the number of registered tools.
CImplement a retry policy that uses exponential backoff and jitter.
DSpit uploaded content into smaller files.
Question #15Part 1Implement generative AI and agentic solutions

You need to configure Agent1 so that it satisfies the security and compliance requirements. Which capability should you use?

Aself-harm content filtering
Bprompt shields
CPersonally identifiable information (PII) Detection
Dviolence content filtering
Question #16Part 1Implement generative AI and agentic solutions

You need to recommend a solution for assessing the responses that Agent1 generates when it relies on the product information stored in storage1, and the solution must satisfy the technical requirements. What should you include in the recommendation?

Aa Retrieval Augmented Generation (RAG) evaluator
Ba custom guardrail
Cmodel fine-tuning
Da groundedness evaluator
Question #17Part 1Implement generative AI and agentic solutions

You need to configure Agent1 so that it answers customer questions only about Contoso products, in line with the business requirements. What should you do?

AModify the system message instructions.
BAdd few-shot examples.
CApply top-p sampling.
DIncrease the value of the temperature parameter.
Question #18Part 1Implement information extraction solutions

You need to recommend an invoice review solution that addresses the issue reported by the finance department. What should you include in the recommendation?

Achat completions
BAzure Document Intelligence in Foundry Tools
CAzure Content Understanding in Foundry Tools
DImage Analysis
Question #19Part 1Implement information extraction solutionsSelect 2

You need to configure an indexing pipeline for Agent1 so that it can retrieve the relevant product information from storage1. The solution must satisfy the technical requirement. Which two built-in skills should you use? Each correct answer presents part of the solution. NOTE: Each correct selection is worth one point.

AAzure OpenAI Embedding
BEntity Recognition
CText Split
DMerge
ELanguage Detection
Question #20Part 1Implement generative AI and agentic solutions

You need to recommend a solution that supports the planned changes and technical requirements so that Agent1 can use the product information stored in storage1. What should you include in the recommendation?

AAzure Translator in Foundry Tools
BGrounding with Bing Search
CAzure AI Search
DAzure Document intelligence in Foundry Tools
Question #21Part 1Implement information extraction solutions

You have an application that processes scanned PDF invoices. The invoices use varied layouts and include tables that span multiple pages. Your pipeline uses optical character recognition (OCR) to extract totals and invoice numbers, but the results are frequently incorrect because the document's structure is ignored. You need a solution that provides OCR, layout analysis, and field extraction that generalizes across templates. The solution must NOT require training a custom model, and it must minimize administrative effort. What should you include in the solution?

AAzure Language in Foundry Tools
BAzure Content Understanding in Foundry Tools
Can Azure Machine Learning model
Question #22Part 1Implement information extraction solutions

You have a Microsoft Foundry project named Project1 that contains an application for processing PDF vendor invoices. You need to configure Azure Document Intelligence in Foundry Tools to produce Markdown output that preserves the sections and table structure of the PDFs. The solution must minimize development effort. What should you do?

AConfigure output=figures when you analyze the PDF.
BConfigure content=markdown when you analyze the document.
CIncrease the confidence threshold.
DSet the output_content_format=ContentFormat.MARKDOWN value.
Question #23Part 1Plan and manage an Azure AI solution

You are building a web app named App1 that generates responses by using a model deployed to a Microsoft Foundry project named Project1. Before sending prompts to the model, App1 must retrieve documents by using Azure AI Search. You need to integrate Project1 and App1. The solution must meet the following requirements: - Multiple client applications must use the same search configuration. - A security policy must prevent key-based authentication. - Administrative effort must be minimized. What should you do?

ACreate a custom HTTP connection in Foundry and manually configure Azure AI Search endpoints per application.
BConfigure an Azure AI Search connection in Project1 and reference the connection in each application.
CCall Azure AI Search directly from each application by using Microsoft Entra authentication.
DEnable a managed identity for each application and call Azure AI Search directly.
Question #24Part 1Plan and manage an Azure AI solution

You have an Azure Speech in Foundry Tools resource that hosts a custom speech-to-text model deployed to a custom endpoint, and an agent uses that endpoint for real-time speech recognition. The custom speech-to-text model is nearing its expiration date. What is the expected behavior once the model expires?

ASpeech recognition requests will return a 4xx error until a new custom model is deployed.
BSpeech recognition requests will continue to use the expired custom model until the model is removed manually.
CSpeech recognition requests will fall back to the most recent base model for the same locale.
DThe custom model will be deleted automatically when the model expires.
Question #25Part 1Implement generative AI and agentic solutions

Your Microsoft Foundry project includes a customer support agent that calls an internal knowledge API tool before it generates responses. Users are reporting the following issues: - Certain requests take longer than 15 seconds to complete. - Certain responses are incorrect, even though the knowledge API returns the expected data. You need to inspect individual agent runs to view the ordered sequence of large language model (LLM) calls, tool invocations, and timing information. Which observability capability should you use?

Atoken usage
Bmonitoring
Csafety metrics
Dtracing
Question #26Part 1Implement information extraction solutions

You have a Microsoft Foundry project that ingests scanned PDF invoices stored in Azure Blob Storage. Each invoice contains printed line items and uses a table-based layout. The extracted results are stored as structured JSON and used as grounding data for an agent in a Retrieval Augmented Generation (RAG) solution. You need to create a single analyzer that meets the following requirements: - Extracts the invoice number, invoice date, vendor name, and total amount across varying templates - Returns confidence scores so that results with confidence below 0.80 can be routed for supervisor review What should you use?

Aa Foundry agent that has groundedness guardrails enabled to extract invoice fields and confidence scores
Ba custom Azure Content Understanding in Foundry Tools analyzer that defines the required fields as the extracted fields and the returned confidence scores for routing
Cthe Azure Content Understanding in Foundry Tools prebuilt-layout analyzer
Dthe Azure Content Understanding in Foundry Tools prebuilt-documentSearch analyzer and search.score from the Azure AI Search results for routing
Question #27Part 1Implement generative AI and agentic solutions

You have a Microsoft Foundry project that contains an agent. The agent generates summaries from retrieved policy documents. You need to improve the completeness of the responses. The solution must be implemented in the application code's logic before the responses are returned. What should you do?

AAdd a retry evaluation before the responses are returned.
BDecrease the value of the max_tokens parameter.
CSwitch to Retrieval Augmented Generation (RAG).
DReplace the model with a smaller deployment.
Question #28Part 1Implement generative AI and agentic solutions

You have a Microsoft Foundry project that contains a high-traffic agent. Following a recent update, operational costs rise significantly, even though monitoring confirms that the volume of user traffic to the agent has stayed the same. You suspect that changes to the request or response characteristics are behind the increase, and you need to determine whether the added cost comes from the model input size, the model output size, or expanded tool usage. Which observability capability should you use?

Alatency
Bevaluation metrics
Crun success rate
Dtoken usage
Question #29Part 1Implement information extraction solutions

You have a Microsoft Foundry project that contains an agent. The agent's knowledge source is a set of scanned PDF troubleshooting guides stored in Azure Blob Storage. The guide pages use two-column layouts and contain tables. You use Azure Content Understanding in Foundry Tools to process the PDFs, and you plan to ingest the processed content into an index for Retrieval Augmented Generation (RAG) while storing the extracted fields for downstream automation. Stakeholders need to be able to verify where each extracted field value originated in the original PDF, and route low-reliability extractions for manual review. You need the Content Understanding document analyzer output to include a per-field confidence score and source grounding to locations within the source document. What should you do?

ASet enableSegment to true.
BProvide labeled samples.
CEnable estimateFieldSourceAndConfidence.
DConfigure the analyzer to use generative extraction for all fields.
Question #30Part 1Implement generative AI and agentic solutions

You have a Microsoft Foundry project that contains three agents, as shown in the following table. ![Question Image](https://cdn.examcademy.com/images/questions/1783676237999-9kfjzr06.png) You need to orchestrate these agents so that handling of customer requests meets the following requirements: - Support a deterministic, step-based process that uses conditional branching and shared state across the agents. - Optionally trigger a ticket action based on the triage result. - Minimize development effort. What should you include in the solution?

Aa workflow
Bthreads and runs without a workflow
Ca multi-agent group chat session
Dseparate agent runs coordinated in the application code
Question #31Part 1Implement generative AI and agentic solutions

You have a Microsoft Foundry project that generates product marketing images from text prompts. After several images are published, your company's legal team identifies a competitor's logo on a sign in the background of one of the images. You need to remove only the logo while preserving the rest of the image. What should you do?

AApply a mask-based inpainting edit to the part of the image that contains the logo.
BIncrease the prompt guidance strength.
CModify the original prompt to exclude brand names.
DRerun the prompt by using a different random seed.
Question #32Part 1Plan and manage an Azure AI solution

You have a Microsoft Foundry project that contains a model deployment, and an application calls that deployment by using the Azure OpenAI v1 API together with DefaultAzureCredential. Developers at your company receive HTTP 403 errors when they send inference requests, even after they run `az login`. You need to ensure that the developers can perform model inference, and the solution must follow the principle of least privilege. Which role-based access control (RBAC) role should you assign to the developers?

ACognitive Services User
BCognitive Services OpenAI User
CContributor
DCognitive Services Data Reader
Question #33Part 1Plan and manage an Azure AI solution

You have a Microsoft Foundry project that uses Azure AI Search to ground an agent in internal documentation. After a recent content update, users report that the agent's answers have become less accurate. You need to determine whether the retrieved content is negatively affecting the model's generated responses. Which observability signal should you review?

Aindexer status and failure history
Blatency breakdown traces
Cprediction drift metrics
Dgroundedness evaluation metrics
Question #34Part 1Implement generative AI and agentic solutions

You have a chat application in a Microsoft Foundry project and a vectorized index in Azure AI Search. You need to connect to the index so that the solution meets the following requirements: - Complex questions must retrieve information from multiple chunks. - Multi-turn conversations must influence retrieval planning. - Retrievals must run in parallel to reduce latency. Which retrieval approach should you use?

Aiterative retrieval
Bagentic Retrieval Augmented Generation (RAG)
Cchain of thought
Dclassic Retrieval Augmented Generation (RAG)
Question #35Part 1Implement generative AI and agentic solutions

You have a customer support agent that uses the Microsoft Foundry Agent Service. Customers sometimes return to a session days later to continue the same support case, and the agent must resume with the full historical context. The agent must provide: - Multi-turn continuity within the session. - Cross-session continuity for the same case. - Access to the full interaction history, including user messages, agent messages, tool calls, and tool outputs. You need to ensure that the agent automatically reloads the complete history on every new turn. What should you do?

ACreate and reuse a conversation by storing the conversation’s ID and supplying the ID on subsequent requests.
BPersist only the final model response stored in the client application and prepend the response to future prompts.
CEnable memory summarization on the agent definition to persist the context automatically.
Question #36Part 1Implement text analysis solutions

You have an application named App1 that uses a Microsoft Foundry multimodal model deployment. App1 performs optical character recognition (OCR) on uploaded images and appends the OCR results to the prompt as additional context. Some of the uploaded images contain embedded text. You need to prevent the model from processing potentially malicious instructions contained in that text. What should you use?

Aimage moderation
Bprompt shields for documents
Cprotected material text
Dprompt shields for user prompts
Question #37Part 1Implement generative AI and agentic solutions

You have a Microsoft Foundry project that contains an agent and an image-generation model deployment. The agent generates new images from user-supplied product photos. You need to ensure that the generated images retain the product's identity and visual characteristics from the supplied photo. What should you do?

ASet the input_fidelity parameter to high.
BApply a groundedness detection filter.
CInclude a prompt and input image in the request.
DDecrease the value of the temperature parameter.
Question #38Part 1Implement information extraction solutions

You have a Microsoft Foundry project that contains an agent. The agent uses a knowledge source built from documents stored in Azure Blob Storage. The documents include digitally scanned PDFs containing tables that span multiple pages. Your current ingestion job extracts only plain text, which causes the loss of table structure, headings, and page-number metadata. Users frequently ask questions that require retrieving specific table rows across pages. You need to configure an ingestion job for a Retrieval Augmented Generation (RAG) pipeline that: - Performs optical character recognition (OCR) on the scanned PDFs - Preserves tables and headings as structure-aware chunks - Stores page-number metadata with each chunk How should you configure the ingestion job?

AUse advanced data parsing to reingest the documents.
BUse OCR and page-level chunking.
CUse page-level OCR extraction and store each page as a single chunk.
DUse basic parsing and fixed-size chunking.
Question #39Part 1Implement generative AI and agentic solutions

Proposed solution: Configure a prompt shield for user prompts. Does this solution meet the goal?

AYes
BNo
Question #40Part 1Implement computer vision solutions

Proposed solution: Configure image moderation to block unsafe content before the images are processed. Does this solution meet the goal?

AYes
BNo
Question #41Part 1Implement generative AI and agentic solutions

Proposed solution: Configure a prompt shield for documents. Does this solution meet the goal?

AYes
BNo
Question #42Part 1Implement text analysis solutions

Proposed solution: Configure protected material detection. Does this solution meet the goal?

AYes
BNo
Question #43Part 1Implement information extraction solutions

You have a Microsoft Foundry project that contains an agent. The agent uses Azure AI Search as its retriever. You plan to ingest PDFs into an Azure AI Search index so the agent can ground its responses in text from both the documents and their embedded images. Users require citations that link back to the source files. You need to ensure that, during indexing, the images are extracted into a structure that the built-in optical character recognition (OCR) skill can use as input. Which indexing approach should you use?

Aan indexer to extract image data into a normalized_images collection
Ba Shaper skill to restructure the OCR input
Ca skillset to run the OCR skill directly against the content field of the index
Dthe outputFieldMappings parameter to write image data to a searchable field
Question #44Part 1Implement generative AI and agentic solutionsSelect 2

You have a Microsoft Foundry project that contains a prompt agent used by a customer support web app. The agent is invoked from a Python service that does not run in the Foundry portal. You need to implement end-to-end tracing to capture latency breakdowns and exceptions across agent runs. Which two components can you use? Each correct answer presents a complete solution. NOTE: Each correct selection is worth one point.

Aa Log Analytics workspace
BApplication Insights
COpenTelemetry
Dthe Azure Monitor Agent
EMicrosoft Sentinel
Question #45Part 1Implement information extraction solutions

You have a Microsoft Foundry project that contains an agent. You need to process mixed-format documents containing scanned text, tables, and multicolumn layouts. The extracted content must preserve the document's structure and be converted to Markdown format for downstream reasoning. What should you configure first?

Aan Azure Language in Foundry Tools text analysis model deployment
Ba generative chat completion request
Can Azure OpenAI Responses API call that uses a multimodal model
Dan Azure Content Understanding in Foundry Tools analyzer
Question #46Part 1Implement computer vision solutions

You are building an image-editing workflow in a Microsoft Foundry project. The workflow must meet the following requirements: - Background objects can be removed by applying a mask-based inpainting edit. - The original lighting and style of the edited images are preserved. - The built-in image editing controls are used, NOT a custom model. You need to ensure that image edits are applied exclusively inside the masked area. How should you configure the workflow?

ASet generation mode to image_variation and provide the original image as a reference.
BEnable text_to_image mode and a prompt describing the desired background removal.
CEnable image_to_image mode and a high-strength value to regenerate the full image based on the prompt.
DEnable mask_inpainting and supply both the input image and a mask indicating which part of the image to modify.
Question #47Part 1Implement generative AI and agentic solutions

You have a Microsoft Foundry project that serves a high-volume chat application. Most of the requests are simple FAQs, but some require advanced reasoning. You need to reduce cost and latency for the common queries without degrading the quality of responses to the complex questions. What should you do?

ARoute all the requests to a smaller model.
BUse a model cascade that routes the requests to different models.
CIncrease the value of the max_tokens parameter for all the requests.
DRoute all the requests to the most capable model.
Question #48Part 1Implement generative AI and agentic solutions

You are creating an agent workflow in a Microsoft Foundry project to support natural voice interactions. The agent must receive continuous audio input, convert that input into text for reasoning, and return spoken responses to the user. The workflow must meet the following requirements: - Support turn-taking dynamics, where the agent can begin generating speech output before the user finishes speaking - 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?

AUse batch transcription to convert the audio input and return text responses from the agent.
BUse real-time speech to text for incoming audio and text to speech for agent responses.
CUse an embeddings model to encode the audio, and then decode the audio into text and speech.
DUse speech translation to convert the audio into another language and return the translated text.
Question #49Part 1Plan and manage an Azure AI solution

You are planning a Microsoft Foundry project named Project1 that will host multiple agents, and every agent will need to access the same Azure AI Search resource. You need to recommend a solution that centrally manages the Azure AI Search credentials within Project1, and the solution must be applied across all the agents. What should you recommend?

AEnable role-based access control (RBAC) for the Azure AI Search resource.
BDisable key-based access control on the Azure AI Search resource.
CAdd a connection to the Azure AI Search resource.
DCreate a managed private endpoint that connects to the Azure AI Search resource.
Question #50Part 1Implement generative AI and agentic solutions

You need to configure personalized interactions for Agent1 so that the solution satisfies the business requirements. What should you include in the solution?

Aknowledge
Bmemory
Cguardrails
Dtools
Question #51Part 1Implement generative AI and agentic solutionsSelect 2

You have a Microsoft Foundry project containing a Retrieval Augmented Generation (RAG) chat solution used by customer support agents. You are adding an automated pre-production evaluation step to a CI/CD pipeline named Pipeline1. The evaluation will run against a labeled test dataset containing support questions along with the expected grounding context. You need to ensure that Pipeline1 fails if unsupported content or a retrieval mismatch exceeds a defined threshold, where: - Responses include claims that are not supported by the retrieved source content. - The retrieved source content does not align with the labeled expected context. Which two built-in evaluators should you use in Pipeline1? (Each correct answer presents part of the solution.) Note: Each correct selection is worth one point.

ARetrieval
BFluency
CCoherence
DGroundedness
EResponse Completeness

📢 Unlock Full Access to Success!

"The content displayed here is a promotional preview and contains only 50% of the actual exam database. To access the complete set of updated questions, please upgrade to the Full Version."

👉 Click the button and follow the instructions to secure your full access immediately!