AI-901 Exam Flashcards

Q: What do AI-901 flashcards help you review?

These AI-901 flashcards review the concepts candidates need to recognize quickly: responsible AI principles, Microsoft Foundry workflow, generative AI terms, agents, Azure AI services, and common language, speech, vision, and extraction workloads.

Q: Are these AI-901 flashcards enough by themselves?

Flashcards are best for quick recall and service distinctions. Pair them with Microsoft Learn modules, hands-on Foundry practice, and scenario questions before scheduling the exam.

Q: Which AI-901 areas should get the most review time?

The local exam metadata shows Microsoft Foundry implementation as the larger skill area, so spend extra review time on deploying models, testing prompts, building chat apps, creating agents, and using Content Understanding.

Question 1

Microsoft Foundry

Accepted Answer

Microsoft Foundry is the workspace for building, testing, deploying, and managing AI apps and agents on Azure. For AI-901, connect Foundry to model deployment, prompt testing, agents, tools, and app integration.

Question 2

Foundry project

Accepted Answer

A Foundry project groups the resources for one AI solution, such as deployments, data connections, tools, and evaluation assets. It keeps solution work organized instead of scattering pieces across separate portals.

Question 3

Model catalog

Accepted Answer

The model catalog is where you compare available models by capability, modality, cost, and deployment option. Pick the model that matches the task, not just the most powerful model.

Question 4

Model deployment

Accepted Answer

Deployment makes a selected model callable by an application. Without a deployment, a model may appear in the catalog but there is no configured endpoint for inference requests.

Question 5

Chat playground

Accepted Answer

The chat playground is an interactive way to test a deployed model, prompts, and parameters before writing code. Use it to learn behavior quickly and reduce trial-and-error in an app.

Question 6

Foundry SDK

Accepted Answer

The Foundry SDK lets code connect to a project, call model deployments, and build lightweight clients or agents. It is the programmatic path after a portal prototype works.

Question 7

Azure AI services

Accepted Answer

Azure AI services provide ready-made APIs for common workloads such as vision, language, and speech. Use them when you need proven capabilities without training a custom model from scratch.

Question 8

Fairness

Accepted Answer

Fairness means an AI solution should avoid systematically disadvantaging people or groups. The consequence is design and testing that look for biased outcomes, not just high overall accuracy.

Question 9

Reliability and safety

Accepted Answer

Reliability and safety focus on consistent behavior and harm reduction under expected and unexpected conditions. Testing, monitoring, fallback behavior, and content filters support this principle.

Question 10

Privacy and security

Accepted Answer

Privacy and security require protecting training data, prompts, outputs, and connected systems. A useful AI app can still fail this principle if it leaks personal or confidential information.

Question 11

Inclusiveness

Accepted Answer

Inclusiveness means the AI solution should work for people with different abilities, backgrounds, and access needs. Accessibility is not a cosmetic add-on; it affects who can benefit from the system.

Question 12

Transparency

Accepted Answer

Transparency means users and stakeholders can understand what the system can do, what it cannot do, and when AI is being used. It reduces misplaced trust in model output.

Question 13

Accountability

Accepted Answer

Accountability means people and organizations remain responsible for AI behavior and outcomes. A model cannot own a policy decision, approval workflow, or failure response.

Question 14

Content safety

Accepted Answer

Content safety detects and blocks harmful text or images, such as violent, hateful, or self-harm content. It is especially important when users can submit open-ended prompts.

Question 15

Human-in-the-loop

Accepted Answer

Human-in-the-loop design sends sensitive or uncertain AI outcomes to a person for review. It is useful when a wrong answer could harm a person, business, or legal process.

Question 16

Generative language model

Accepted Answer

A generative language model creates text by using learned patterns to predict likely next tokens. It can produce new responses, but fluency does not guarantee factual correctness.

Question 17

Token

Accepted Answer

A token is a chunk of text processed by a language model. Prompts, retrieved context, and generated answers all consume tokens, which affects cost, latency, and context limits.

Question 18

Context window

Accepted Answer

The context window is the amount of text and other input a model can consider at once. If important information falls outside it, the model cannot use that information directly.

Question 19

Temperature

Accepted Answer

Temperature controls response variation. Lower values make output more predictable; higher values make it more diverse but can reduce consistency for factual or formatted tasks.

Question 20

Max tokens

Accepted Answer

Max tokens limits how much text the model can generate. It is a guardrail for answer length and cost, but setting it too low can cut off useful responses.

Question 21

Embeddings

Accepted Answer

Embeddings turn text or other content into numeric vectors that represent meaning. They make semantic search possible because similar ideas can be found even when wording differs.

Question 22

Semantic search

Accepted Answer

Semantic search retrieves content by meaning instead of only exact keyword matches. It is useful when users ask questions in different words than the source documents use.

Question 23

Retrieval-augmented generation (RAG)

Accepted Answer

RAG retrieves relevant source content and adds it to the prompt so the model can answer with grounding. It improves domain accuracy without changing the base model weights.

Question 24

RAG vs fine-tuning

Accepted Answer

Use RAG to ground answers in changing or private content. Use fine-tuning when you need the model to learn a repeated style, task pattern, or behavior from examples.

Question 25

Hallucination

Accepted Answer

A hallucination is a confident answer that is unsupported or false. Grounding, citations, content limits, and human review reduce risk but do not remove it entirely.

Question 26

Multimodal model

Accepted Answer

A multimodal model can work with more than one input or output type, such as text plus images. Use it for tasks like answering questions about a screenshot or chart.

Question 27

Generative AI vs predictive AI

Accepted Answer

Generative AI creates new content, such as text or images. Predictive AI estimates a value, class, or future outcome from patterns in data.

Question 28

AI agent

Accepted Answer

An AI agent uses a model plus instructions and tools to work toward a goal across steps. It differs from a simple chat response because it can decide when to call actions.

Question 29

Agent tools

Accepted Answer

Tools let an agent do work beyond text generation, such as searching data, calling an API, or running a workflow. Tool design controls what the agent can actually affect.

Question 30

Agent instructions

Accepted Answer

Instructions define an agent's role, boundaries, and expected behavior. Clear instructions reduce unwanted actions and make tool use more predictable.

Question 31

System message

Accepted Answer

A system message sets high-priority guidance for a chat model, such as role, tone, limits, and safety rules. It is more durable than one-off user wording.

Question 32

Few-shot prompting

Accepted Answer

Few-shot prompting includes sample inputs and outputs so the model can follow the pattern. It changes prompt context, not the trained model weights.

Question 33

Prompt constraints

Accepted Answer

Prompt constraints tell the model what format, sources, tone, or boundaries to follow. They make output easier to validate and safer to use in applications.

Question 34

Sentiment analysis

Accepted Answer

Sentiment analysis estimates whether text expresses positive, negative, neutral, or mixed feeling. It is useful for reviews and feedback, not for proving factual claims.

Question 35

Key phrase extraction

Accepted Answer

Key phrase extraction identifies important terms that summarize what a text is about. It helps tag or scan documents without reading every sentence.

Question 36

Named entity recognition

Accepted Answer

Named entity recognition finds people, places, organizations, dates, and similar entities in text. It extracts structured signals from otherwise unstructured language.

Question 37

Summarization

Accepted Answer

Summarization shortens text while preserving the main meaning. Extractive summaries reuse key source sentences; abstractive summaries restate the ideas in new wording.

Question 38

Translation

Accepted Answer

Translation converts content from one language to another. It is an NLP workload when translating text and a speech workload when translating spoken audio.

Question 39

Speech to text

Accepted Answer

Speech to text transcribes spoken audio into written words. It supports captions, meeting notes, voice commands, and searchable audio archives.

Question 40

Text to speech

Accepted Answer

Text to speech turns written text into spoken audio. It is used for narration, accessibility, call center responses, and voice experiences.

Question 41

Speaker recognition

Accepted Answer

Speaker recognition identifies or verifies a person by voice characteristics. It is different from speech recognition, which determines the words being spoken.

Question 42

Image classification vs object detection

Accepted Answer

Image classification labels the whole image. Object detection identifies individual objects and where they are located, often with bounding boxes.

Question 43

Optical character recognition (OCR)

Accepted Answer

OCR extracts printed or handwritten text from images and documents. It is the right workload when the goal is to read visible text, not classify the image.

Question 44

Image generation vs image analysis

Accepted Answer

Image generation creates a new image from a prompt. Image analysis interprets an existing image, such as labeling scenes, reading text, or finding objects.

Question 45

Azure AI Vision

Accepted Answer

Azure AI Vision supports image analysis tasks such as OCR, image captions, object detection, and visual tagging. Map it to scenarios that start with image or video content.

Question 46

Azure AI Language

Accepted Answer

Azure AI Language supports text analytics such as sentiment, entities, key phrases, language detection, and summarization. Map it to scenarios built around written language.

Question 47

Azure AI Speech

Accepted Answer

Azure AI Speech supports speech to text, text to speech, speech translation, and speaker recognition. Map it to scenarios where audio is the main input or output.

Question 48

Azure Content Understanding

Accepted Answer

Azure Content Understanding extracts structured information from documents, images, audio, and video. Use it when the task is to pull fields, topics, or key details from content.

Question 49

Document field extraction

Accepted Answer

Document field extraction finds values such as dates, totals, names, and identifiers in forms or invoices. The goal is structured output, not just a text transcript.

Question 50

Classification vs regression

Accepted Answer

Classification predicts a category, such as approve or deny. Regression predicts a numeric value, such as price or demand.

Free AI-901 Exam Flashcards

Filter by Topic

Jump to Card

About These AI-901 Flashcards

Topics Covered

Frequently Asked Questions

Microsoft Certified: Azure AI Fundamentals (AI-901)

Explore More Microsoft Azure Certifications

Azure AZ-104

Azure AZ-900

Azure AI-900

Azure DP-700

Azure DP-600

Azure DP-900

More From This Family