AI-103 Multiple Select — 50 Questions

Question 1

Which TWO components are essential for creating an effective system prompt?

Accepted Answer

A clear definition of the agent's persona and objective.. Option A is correct because an effective system prompt must establish the agent's persona and objective, giving the model a clear role, tone, and goal that shape all subsequent responses. Option D is correct because system prompts need explicit constraints and instructions for edge cases or disallowed topics, which set behavioral boundaries and safety guardrails for the agent. Options B, C, and E are not essential: authorized-user lists are typically enforced by authentication and access-control systems rather than the prompt, the base model's full training dataset is not something the prompt author supplies, and data center hardware details are irrelevant to prompt design.

Answer

A list of all users authorized to use the agent.

Answer

The full training dataset of the base model.

Answer

A list of all hardware components in the data center.

Question 2

You are managing Azure OpenAI deployments and need to monitor token consumption and error rates. Which TWO Azure Monitor features should you use to analyze this telemetry? Each correct answer presents part of the solution.

Accepted Answer

Azure Monitor Metrics Explorer to graph real-time metrics like Total Calls and Latency.. Option A is correct because Azure Monitor Metrics Explorer lets you plot near real-time platform metrics for Azure OpenAI, including Total Calls, Token Usage (prompt/completion tokens), and Latency, which directly addresses monitoring token consumption and error rates at a glance. Option C is correct because Azure OpenAI diagnostic settings can route request/response logs and metrics to a Log Analytics workspace, where Kusto Query Language (KQL) queries enable deep analysis of per-request token counts, status codes, and error patterns over time. Together, Metrics Explorer provides fast visual monitoring while Log Analytics with KQL provides granular, queryable telemetry. Option B is incorrect because Azure DevOps commit history tracks source code changes, not Azure OpenAI runtime telemetry. Option D is incorrect because Microsoft 365 compliance center content search is for eDiscovery of Microsoft 365 content, not Azure Monitor telemetry. Option E is incorrect because Azure Bastion session monitoring relates to secure RDP/SSH access to VMs, not OpenAI token or error metrics.

Answer

Azure DevOps commit history dashboard

Answer

Microsoft 365 compliance center content search

Answer

Azure Bastion session monitor

Question 3

Your company wants to track and allocate Azure AI service costs by department. Which TWO mechanisms can assist with this requirement? (Choose two.)

Accepted Answer

Using Azure Cost Management filters and cost allocation rules to generate chargeback reports.. Option A is correct because Azure Cost Management supports filters (by resource group, tag, service, subscription, etc.) and cost allocation rules that let you split shared costs across departments, enabling accurate chargeback/showback reports for Azure AI services. Option E is correct because applying department-specific tags such as Department: Marketing to Azure AI resources lets Cost Management group and filter spend by tag, which is the standard way to attribute AI service costs to each department. Option B is incorrect because a single untagged, unsegmented subscription provides no dimension to separate or allocate costs by department. Option C is incorrect because deactivating Azure Cost Management removes the very reporting and allocation capability needed for cost tracking. Option D is incorrect because the Free (F0) tier only affects pricing/limits of certain AI services and does not provide any cost tracking or allocation mechanism.

Answer

Sharing a single Azure subscription across all departments without using tags or resource groups.

Answer

Deactivating Azure Cost Management to reduce management overhead.

Answer

Provisioning all AI resources in the Free (F0) tier.

Question 4

Which TWO factors directly influence the embedding quality and retrieval relevance in an Azure AI Search vector retrieval pipeline? (Choose two.)

Accepted Answer

The choice of embedding model (e.g., text-embedding-3-large vs text-embedding-3-small) and its dimensionality.. Option B is correct because the embedding model determines the semantic quality of the vectors stored in the Azure AI Search index: text-embedding-3-large produces higher-fidelity, higher-dimensional vectors (3072 dimensions) than text-embedding-3-small (1536 dimensions), directly affecting how well semantic similarity matches user intent during vector search. Option E is correct because chunking strategy and chunk size control the granularity of the indexed content; chunks that are too large dilute the embedding with unrelated content, while chunks that are too small lose context, so both the segmentation method (e.g., fixed-size, sentence-aware, or document-layout-aware) and the chunk length materially affect retrieval relevance. Options A and C are incorrect because background color and font family are visual formatting attributes that are not captured by text embedding models and have no bearing on vector similarity. Option D is incorrect because the end user's browser version affects client-side rendering and request handling, not the embedding quality or the relevance scoring performed by Azure AI Search.

Answer

The background color of the source documents in blob storage.

Answer

The font family used in the original PDF documents.

Answer

The client browser version used by the end user.

Question 5

As part of responsible AI practices in Azure AI Foundry, which TWO actions should you perform to evaluate and mitigate model fairness and safety risks before deployment? (Choose two)

Accepted Answer

Run automated evaluations in Azure AI Foundry to measure metrics such as groundedness, relevance, and protected material presence.. Option B is correct because Azure AI Foundry's automated evaluation flows let you quantify safety and quality metrics—groundedness, relevance, coherence, fluency, and protected-material/hate-and-unfairness scores—so you can objectively assess fairness and safety risks before deployment. Option D is correct because adversarial testing (red teaming) in Azure AI Foundry systematically probes the model with prompt injections, jailbreak attempts, and other malicious inputs to surface unintended behaviors and safety gaps that must be mitigated prior to release. Option A is wrong because internal-only audiences do not exempt an application from responsible AI security and safety reviews; risk assessments apply regardless of user population. Option C is wrong because removing system prompts strips guardrails and grounding instructions, increasing unsafe or off-topic outputs rather than enabling meaningful evaluation. Option E is wrong because hardcoding responses is not a fairness/safety evaluation technique and would defeat the purpose of testing a generative model's behavior.

Answer

Bypass security reviews if the application is intended for internal enterprise employees only.

Answer

Remove all system prompts to allow the model complete autonomy during evaluation runs.

Answer

Hardcode responses for all possible user inputs to eliminate model non-determinism entirely.

Question 6

Which TWO image file formats are natively supported by Azure AI Vision for image analysis? (Choose two.)

Accepted Answer

JPEG. Azure AI Vision's Image Analysis API natively accepts JPEG (option D) and PNG (option E) as image payloads, since these are the standard raster formats the service decodes for feature extraction such as captioning, OCR, and object detection. JPEG is supported because it is the most common compressed photographic format, and PNG is supported because it preserves lossless detail and transparency for graphics and text-heavy images. The remaining options do not belong: MP3 (A) and WAV (C) are audio codecs, and MKV (B) is a video container format, none of which are image file formats accepted by the Image Analysis endpoint.

Answer

MP3

Answer

MKV

Answer

WAV

Question 7

You are optimizing an enterprise RAG application in Azure AI Foundry for high accuracy and minimal latency. Which THREE advanced retrieval techniques should you consider implementing? (Choose THREE)

Accepted Answer

Semantic ranking to re-rank top search results using deep learning models. Option A (Semantic ranking) is correct because Azure AI Search's semantic ranker applies deep-learning language models to re-rank the top BM25/vector results, promoting the most contextually relevant passages and directly improving RAG answer accuracy. Option C (Hybrid search combining full-text BM25 and vector embeddings) is correct because fusing keyword and dense-vector retrieval via Reciprocal Rank Fusion captures both exact term matches and semantic similarity, which raises recall and precision over either method alone. Option E (Query expansion and re-writing) is correct because enriching the user prompt with synonyms and related terms broadens the candidate set and aligns the query with the indexed content, improving retrieval quality for ambiguous or short queries. Option B does not belong because random sentence selection without indexing provides no relevance signal or deterministic retrieval, guaranteeing poor accuracy. Option D does not belong because disabling vector search and relying on random string matching discards semantic retrieval entirely, which destroys both accuracy and the ability to handle natural-language queries.

Answer

Using random sentence selection without indexing

Answer

Disabling vector search entirely to rely solely on random string matching

Question 8

You are troubleshooting a low confidence score on specific fields extracted by your Azure AI Document Intelligence custom template model. Which TWO actions can help improve the extraction confidence for those fields? (Choose TWO)

Accepted Answer

Ensure all training documents are of high visual quality and free from blur or heavy skew.. Option C is correct because custom template models learn field positions and visual patterns from the labeled samples, so blurry, skewed, or low-quality training documents degrade the model's ability to reliably locate and read those fields, producing low confidence scores; supplying sharp, straight, high-quality scans directly improves feature extraction and OCR accuracy. Option D is correct because low confidence on specific fields usually indicates the model has not seen enough layout variation for those fields, so adding diverse training documents that capture the different layouts, fonts, and positions where those fields appear lets the model generalize and raise its confidence. Option A is wrong because the confidence threshold in the analyzeDocument request only filters which results are returned or flagged; it does not change the model's actual extraction confidence. Option B is wrong because converting to grayscale and downsampling to 72 DPI reduces image fidelity and typically lowers OCR and extraction quality rather than improving confidence. Option E is wrong because a prebuilt business card model is a fixed, general-purpose model that cannot be trained on your specific fields or layouts, so it cannot improve confidence for your custom template fields.

Answer

Increase the confidence threshold parameter in the analyzeDocument request body to 0.99.

Answer

Convert all training PDFs to grayscale and reduce their resolution to 72 DPI to speed up processing.

Answer

Switch the model type from custom template to a prebuilt business card model.

Question 9

Which THREE of the following are components of a standard Prompt Flow DAG (Directed Acyclic Graph)?

Accepted Answer

Inputs. In a standard Prompt Flow DAG, Inputs (A) are the declared entry points that supply values (for example, a question string or a dataset column) to the flow, making them a required component. Outputs (B) are also required because they define the flow's returned values (such as the model's answer or a score) that downstream consumers or evaluations read. Tools (D) are the executable nodes of the DAG — LLM, Python, Prompt, and built-in tools — and the edges connecting them define the directed acyclic execution order. Model Training Jobs (C) are not part of a Prompt Flow DAG; training is handled by separate Azure Machine Learning job constructs, not flow nodes. Data Labeling Projects (E) are likewise a distinct Azure Machine Learning feature for annotating data and are not components of a Prompt Flow DAG.

Answer

Model Training Jobs

Answer

Data Labeling Projects

Question 10

Which THREE attributes are critical for a successful custom model training set?

Accepted Answer

High-quality images. Option A (High-quality images) is correct because custom model training relies on OCR and layout analysis, so clear, well-lit, high-resolution scans or photos with minimal skew, blur, and noise give the model reliable visual features to learn from. Option B (Consistent labeling across all documents) is correct because supervised training requires ground-truth labels to be applied with the same schema and conventions throughout the dataset; inconsistent labels introduce contradictory signals that degrade accuracy and confuse the model. Option C (Representative samples of all document layouts) is correct because the model must generalize to every form, template, and layout it will encounter in production, so the training set must include examples covering the full variety of structures, fonts, and field placements. Option D is not required because documents need not come from a single printer; in fact, variety in printers, scanners, and capture conditions improves robustness. Option E is not required because there is no fixed minimum of 1,000 pages per model; the needed volume depends on document complexity and diversity, and quality and representativeness matter more than a rigid page count.

Answer

All documents from the same printer

Answer

At least 1,000 pages per model

Question 11

You are designing an enterprise RAG solution using Azure AI Search and Azure OpenAI. You need to ensure data security and compliance across different user permission tiers. Which TWO actions should you implement? (Choose two.)

Accepted Answer

Ensure all data transfers between Azure AI Search and Azure OpenAI utilize TLS 1.2 or higher.. Option A is correct because Azure AI Search and Azure OpenAI communicate over HTTPS endpoints, and enforcing TLS 1.2 or higher protects data in transit against interception or downgrade attacks, which is a baseline requirement for enterprise security and compliance. Option B is correct because Azure AI Search supports document-level access control via security filters (for example, using the user's group IDs in a filterable field or the built-in ACL/rbacScope fields), ensuring each permission tier only retrieves documents its users are authorized to see, which is essential in a multi-tenant RAG solution. Option C is wrong because storing unencrypted authentication tokens in embedding metadata exposes credentials to anyone querying the index and violates token-handling best practices. Option D is wrong because granting admin privileges to all users removes least-privilege enforcement and does not address retrieval latency in a legitimate way. Option E is wrong because disabling managed identities and embedding plaintext connection strings in source code leaks secrets and discards Azure's keyless, identity-based authentication model.

Answer

Store unencrypted user authentication tokens directly inside the embedding vector metadata.

Answer

Grant every user application admin privileges to bypass retrieval latency checks.

Answer

Disable managed identities and store plaintext connection strings in the application source code.

Question 12

When configuring Azure OpenAI Custom Model Evaluation in Azure AI Foundry, which TWO metrics can be computed using LLM-as-a-judge evaluators? (Choose two.)

Accepted Answer

Coherence. Options D and E are correct because Azure AI Foundry's LLM-as-a-judge evaluators are designed to assess the quality of generative AI outputs using a language model as the grader, and Coherence (D) and Relevance (E) are two of the standard quality metrics they compute — Coherence measures how logically well-structured and fluent the response is, while Relevance measures how directly the response addresses the user's query or context. These metrics are part of the built-in evaluation metric set (alongside others such as Fluency, Groundedness, and Similarity) that can be run against a model deployment during custom model evaluation. Options A, B, and C are incorrect because CPU utilization percentage, DNS propagation delay, and disk IOPS are infrastructure and networking performance counters, not language-quality judgments, and they cannot be produced by an LLM-as-a-judge evaluator.

Answer

CPU utilization percentage

Answer

DNS propagation delay

Answer

Disk input/output operations per second (IOPS)

Question 13

You are designing an architecture that processes incoming multilingual support emails using Azure AI Language. Which THREE processing steps should you include in your pipeline? (Choose three.)

Accepted Answer

Execute named entity recognition to extract relevant organizations, locations, and names.. Option C is correct because Azure AI Language's language detection endpoint must be called first to identify each email's primary language, which is essential for routing multilingual content to the appropriate language-specific models. Option A is correct because named entity recognition (NER) extracts entities such as organizations, locations, and person names from the email text, providing structured, actionable information for support workflows. Option E is correct because sentiment analysis and PII detection are supported Azure AI Language features that help gauge customer tone and identify/redact sensitive data in the email documents. Option B is not appropriate because speech-to-text acoustic models are unrelated to processing text emails and training a model per email is impractical. Option D is not appropriate because converting text to raw binary executables serves no analytical purpose and would destroy the text needed for language analysis.

Answer

Train a new speech-to-text acoustic model for every email received.

Answer

Convert all email text into raw binary executable files before analysis.

Question 14

You are conducting a security review of an Azure AI Search service and Azure OpenAI integration. You discover potential security misconfigurations. Which THREE remediation actions should you take to align with Azure security benchmarks? Each correct answer presents part of the solution.

Accepted Answer

Enable diagnostic logging and configure alerts for unauthorized access attempts and HTTP 401/403 errors.. Option B is correct because enabling diagnostic logging and configuring alerts for unauthorized access attempts and HTTP 401/403 errors provides the audit trail and detection capability required by Azure security benchmarks to identify and respond to authentication and authorization failures against Azure AI Search and Azure OpenAI. Option C is correct because disabling public network access once private endpoints are fully implemented enforces network isolation, ensuring traffic reaches the services only through the private endpoint (private link) rather than the public internet, which is a core Azure security benchmark recommendation. Option E is correct because rotating static API keys regularly limits the blast radius of leaked keys, and transitioning clients to Microsoft Entra ID managed identities eliminates long-lived shared secrets entirely by using token-based, identity-driven authentication. Option A does not belong because granting Contributor to anonymous external users violates least privilege and exposes the services to unauthorized modification. Option D does not belong because embedding admin API keys in client-side single-page applications exposes full administrative credentials to anyone inspecting the browser, which is a critical secret-management anti-pattern.

Answer

Grant Contributor permissions to anonymous external users.

Answer

Expose admin API keys in client-side single-page applications for direct access.

Question 15

When establishing a governance strategy for Azure AI resources across multiple cloud teams, which THREE administrative tasks should an administrator perform? (Choose three.)

Accepted Answer

Apply Role-Based Access Control (RBAC) following the principle of least privilege.. Option A is correct because applying Role-Based Access Control (RBAC) with least privilege ensures each cloud team member receives only the permissions needed for their role, such as Reader, Contributor, or specific custom roles, reducing the blast radius of misconfiguration or compromise across Azure AI resources. Option B is correct because Azure Policy can enforce organizational standards such as naming conventions and allowed regions by evaluating resource properties during creation and updates, and it can deny noncompliant deployments or flag them for remediation, which is essential for consistent multi-team governance. Option C is correct because organizing subscriptions under Azure Management Groups creates a hierarchy where policies and RBAC assignments inherit down to child subscriptions, giving administrators a single governance control plane across multiple cloud teams without configuring each subscription individually. Option D is incorrect because disabling Azure Activity Logs would remove the administrative audit trail needed for compliance, security monitoring, and incident investigation, directly undermining governance. Option E is incorrect because assigning the Owner role to all developers violates least privilege and grants excessive control over access and billing, increasing risk rather than establishing sound governance.

Answer

Disable Azure Activity Logs to prevent administrative audit trails.

Answer

Assign the Owner role to all developers to streamline resource creation.

Question 16

You are building an advanced agentic solution in Azure AI Foundry that integrates with external line-of-business systems. Which THREE architectural patterns or features should you incorporate to ensure robustness and safety? (Choose THREE)

Accepted Answer

Human-in-the-loop review for high-impact tool actions. Option A (Human-in-the-loop review for high-impact tool actions) is correct because agentic solutions that call external line-of-business systems can perform destructive or financially significant operations, so gating high-impact tool invocations behind human approval provides a safety control that prevents irreversible mistakes. Option D (Exponential backoff and jitter retry logic for handling API rate limits (HTTP 429)) is correct because external LOB APIs commonly throttle callers and return HTTP 429, and retrying with exponentially increasing delays plus randomized jitter avoids thundering-herd retries and improves robustness against transient throttling. Option E (Structured Outputs with strict JSON Schema validation for tool payloads) is correct because enforcing a strict JSON Schema on tool inputs and outputs guarantees that the agent emits well-formed, type-safe arguments that the downstream LOB system can parse, reducing malformed calls and injection-style errors. Option B is wrong because executing arbitrary bash commands on production servers without validation is a severe security and reliability risk, not a robustness pattern. Option C is wrong because disabling logging and monitoring removes observability, auditability, and the ability to detect failures or misuse, which directly undermines safety and robustness.

Answer

Allowing the agent to execute any bash command directly on production servers without validation

Answer

Disabling all logging and monitoring to maximize execution speed

Question 17

You are designing a text analysis solution using Azure AI Language. Which TWO features are available as prebuilt capabilities without requiring custom model training? (Choose two.)

Accepted Answer

Language detection. Azure AI Language provides it as a prebuilt capability that identifies the language of input text using the ISO 639-1 code, requiring no training data or custom model. Option C (Sentiment analysis) is also correct because it is a prebuilt feature that returns sentiment labels (positive, negative, neutral, mixed) and confidence scores out of the box. In contrast, option A (Custom named entity recognition) and option D (Custom text classification) are custom features that require labeled training data and a trained project before use. Option E (Custom summarization models) is not a prebuilt capability; summarization is offered as prebuilt abstractive/extractive summarization, and any custom summarization model would require training, so it does not fit the 'no custom training' requirement.

Answer

Custom named entity recognition

Answer

Custom text classification

Answer

Custom summarization models

Question 18

When designing agentic workflows in Azure AI Foundry, what are THREE key characteristics or components of agentic design compared to traditional single-turn prompt completion? (Choose THREE)

Accepted Answer

Tool use and external API invocation capabilities. Option A (Tool use and external API invocation capabilities) is correct because agentic workflows in Azure AI Foundry extend beyond text generation by letting agents call tools, functions, and external APIs (for example via function calling or Azure AI Foundry tool connections) to retrieve data or perform actions. Option C (Iterative reasoning and self-reflection loops) is correct because agents can evaluate intermediate results, critique their own output, and re-plan across multiple reasoning steps rather than producing one final completion. Option D (Autonomous planning and task decomposition) is correct because agentic design centers on breaking a high-level goal into subtasks and deciding the order of execution dynamically, often orchestrated by the model itself. Option B is incorrect because hardcoding every conditional path is the opposite of agentic design, which relies on model-driven decisions and orchestration rather than fully procedural branching. Option E is incorrect because single stateless prompt completions without memory describe traditional single-turn completion, whereas agentic workflows typically maintain state, context, and memory across turns.

Answer

Hardcoding every conditional execution path in procedural code

Answer

Executing single stateless prompt completions without memory

Question 19

Which TWO criteria are typically used to evaluate the grounding of an LLM-based application?

Accepted Answer

Relevance. Option A, Relevance, is correct because grounding evaluation checks whether the model's response actually addresses the user's query using the retrieved context, so relevance measures how well the answer aligns with the question and the supplied source material. Option D, Groundedness, is correct because it directly measures whether the generated statements are supported by, or entailed by, the provided reference documents rather than being hallucinated or drawn from the model's parametric memory. Together, relevance and groundedness are the two standard quality dimensions for assessing retrieval-augmented or otherwise grounded LLM applications. The unmarked options do not belong: Latency (B) and Token cost (C) are operational efficiency metrics, not grounding quality criteria, and Model version number (E) is a configuration identifier that says nothing about whether an answer is faithful to its sources.

Answer

Latency

Answer

Token cost

Answer

Model version number

Question 20

You are designing an information extraction solution using Azure AI Document Intelligence. Which TWO features are supported by Custom Neural models? Each correct selection represents a complete solution element.

Accepted Answer

Extraction of key-value pairs and fields defined during training. Option A is correct because Custom Neural models are trained on labeled samples to extract the specific key-value pairs and fields you define during training, returning structured JSON with confidence scores for those fields. Option C is correct because Custom Neural models support table extraction, including documents with variable layouts, by learning the structure from your labeled training data. Option B is incorrect because zero-shot extraction of unseen document types without training data is not a Custom Neural capability; that is handled by prebuilt models or the newer query-field/zero-shot features, not by training a Custom Neural model. Option D is incorrect because voice-to-text transcription is a speech service capability, not a Document Intelligence extraction feature. Option E is incorrect because automatic translation into 100+ languages is provided by Azure AI Translator, not by Custom Neural models.

Answer

Zero-shot extraction of completely unseen document types without any training data

Answer

Real-time voice-to-text transcription of document contents

Answer

Automatic language translation of extracted text into 100+ languages