McAfee Secure

Exam Code: AI-901

Exam Name: Microsoft Azure AI Fundamentals

Certification Provider: Microsoft

Corresponding Certification: Microsoft Certified: Azure AI Fundamentals

Microsoft AI-901 Questions & Answers

Study with Up-To-Date REAL Exam Questions and Answers from the ACTUAL Test

166 Questions & Answers with Testing Engine

"Microsoft Azure AI Fundamentals Exam", also known as AI-901 exam, is a Microsoft certification exam.

Pass your tests with the always up-to-date AI-901 Exam Engine. Your AI-901 training materials keep you at the head of the pack!

Satisfaction Guaranteed

Money Back Guarantee

Testking provides hassle-free money back guarantee with our products. That is because we have 100% trust in the abilities of our professional and experience product team, and our record is a proof of that.

99.6% PASS RATE
Was: $137.49
Now: $124.99

Microsoft AI-901 Practice Test 65

Question 640

An Azure AI Fundamentals solution has this requirement: A team wants to replace a photograph's background while preserving the original product. Which implementation most directly addresses it?

  1. Use image classification for the requested whole-image class
  2. Use segmentation or masked image editing that locks product pixels
  3. Provide the actual image to a capable multimodal or OCR pipeline
  4. Apply bounded retries and respect the service's throughput limit

Explanation

Correct Answer

B:

A mask defines which image area may change. This implementation addresses the precise goal rather than an adjacent AI task.

Incorrect Answers

A:

Image-level classification is distinct from object localization. That is not sufficient here: A mask defines which image area may change.

C:

Visual evidence is needed to read sign content. That is not sufficient here: A mask defines which image area may change.

D:

Too many concurrent requests can exceed resource quota. That is not sufficient here: A mask defines which image area may change.

Question 641

A solution team has selected this control: Use optical character recognition for image text. Which observation is the most direct acceptance evidence?

  1. A returned serial number is stored as OCR text not a generic image tag
  2. The response distinguishes readable values from estimates
  3. The returned string matches the labeled serial number
  4. The output is a new raster image matching the approved icon brief

Explanation

Correct Answer

C:

OCR extracts characters visible in pixels. The expected acceptance evidence is: The returned string matches the labeled serial number. This observation directly tests the stated behavior.

Incorrect Answers

A:

Tags describe concepts while OCR reports character content. This observation does not establish the required result: The returned string matches the labeled serial number.

B:

Visual reasoning is not proof of an exact value when axes are unclear. This observation does not establish the required result: The returned string matches the labeled serial number.

D:

Image generation creates new pixels rather than classifying an existing photo. This observation does not establish the required result: The returned string matches the labeled serial number.

Question 642

An Azure-based AI team must satisfy this objective: A multinational call center needs spoken-language translation for live assistance. Which design choice is best?

  1. Use image segmentation to map visual damage areas instead of assigning one global defect severity
  2. Use a generative language workload with policy-grounded response constraints
  3. Combine speech recognition, language translation, and appropriate speech synthesis
  4. Use noise-aware speech recognition and intent classification with fallback

Explanation

Correct Answer

C:

Speech translation spans audio input, semantic transfer and optional output audio. This implementation addresses the precise goal rather than an adjacent AI task.

Incorrect Answers

A:

Pixel-level region masks localize building damage more precisely than an overall image class label. That is not sufficient here: Speech translation spans audio input, semantic transfer and optional output audio.

B:

Generation produces novel text, unlike choosing a fixed class label. That is not sufficient here: Speech translation spans audio input, semantic transfer and optional output audio.

D:

Speech input quality affects subsequent language classification. That is not sufficient here: Speech translation spans audio input, semantic transfer and optional output audio.

Question 643

An Azure-based AI team must satisfy this objective: A store receives photos of receipts with uncertain tax digits. Which design choice is best?

  1. Run supported image text extraction with field schema and source location
  2. Preserve page identifiers and validate page sequence during extraction
  3. Define a custom analyzer for consistent target field meanings across templates
  4. Use field confidence and source review for ambiguous numeric values

Explanation

Correct Answer

D:

A low-confidence amount must not be silently treated as definitive. This implementation addresses the precise goal rather than an adjacent AI task.

Incorrect Answers

A:

Visual information extraction can map pixels to structured identifiers. That is not sufficient here: A low-confidence amount must not be silently treated as definitive.

B:

Page order and references are part of document provenance. That is not sufficient here: A low-confidence amount must not be silently treated as definitive.

C:

A schema-driven analyzer identifies business fields independent of fixed coordinates. That is not sufficient here: A low-confidence amount must not be silently treated as definitive.

Question 644

The approved design action is: Define required output sections and link citations to actual retrieved passages. Which test result would BEST establish that it worked?

  1. Each cited claim resolves to a real approved source chunk
  2. Injection attempts fail to access protected secrets or tools
  3. A missing case number triggers clarification and no tool operation
  4. Test requests consistently produce parseable objects with required keys

Explanation

Correct Answer

A:

Explicit response structure makes evidence easier to verify. The expected acceptance evidence is: Each cited claim resolves to a real approved source chunk. This observation directly tests the stated behavior.

Incorrect Answers

B:

A user cannot use text to elevate permissions beyond the application policy. This observation does not establish the required result: Each cited claim resolves to a real approved source chunk.

C:

Prompts can define required preconditions but tools must still enforce them. This observation does not establish the required result: Each cited claim resolves to a real approved source chunk.

D:

Explicit examples can improve adherence to bounded output conventions. This observation does not establish the required result: Each cited claim resolves to a real approved source chunk.

Question 645

An Azure AI Fundamentals solution has this requirement: A developer needs to minimize model cost for routine classification. Which implementation most directly addresses it?

  1. Require explicit confirmation and backend authorization before tool execution
  2. Choose a model size using representative quality and cost benchmarks
  3. Honor service throttling and use bounded exponential backoff
  4. Check regional model availability and data handling requirements before deployment

Explanation

Correct Answer

B:

Lower-cost deployment is acceptable only if accuracy and safety floors remain met. This implementation addresses the precise goal rather than an adjacent AI task.

Incorrect Answers

A:

High-impact side effects need permissions independent of conversational language. That is not sufficient here: Lower-cost deployment is acceptable only if accuracy and safety floors remain met.

C:

Rate limits protect the service and uncontrolled retries amplify overload. That is not sufficient here: Lower-cost deployment is acceptable only if accuracy and safety floors remain met.

D:

Not every model or feature is available in every location. That is not sufficient here: Lower-cost deployment is acceptable only if accuracy and safety floors remain met.

Question 646

Troubleshooting report: A retrieved customer note is allowed to override system policy. Which correction is MOST directly targeted to this failure?

  1. Keep policy instructions separate from lower-trust data
  2. Keep publication behind a separate approved deployment step
  3. Create a supported deployment and confirm resource access
  4. Add the actual user content to the chat message sequence

Explanation

Correct Answer

A:

This correction directly addresses the reported failure. High-priority instructions should describe approved behavior and escalation rules. The targeted change is: Keep policy instructions separate from lower-trust data.

Incorrect Answers

B:

A draft or tested agent is not automatically a publicly released service. In the stated case, troubleshooting report: A retrieved customer note is allowed to override system policy; “Keep publication behind a separate approved deployment step” does not target that failure.

C:

The portal provides model selection, deployment and test interfaces for supported resources. In the stated case, troubleshooting report: A retrieved customer note is allowed to override system policy; “Create a supported deployment and confirm resource access” does not target that failure.

D:

The inference service needs task content to generate a relevant answer. In the stated case, troubleshooting report: A retrieved customer note is allowed to override system policy; “Add the actual user content to the chat message sequence” does not target that failure.

Question 647

The approved design action is: Create one agent in the Foundry portal with scoped tool definitions. Which test result would BEST establish that it worked?

  1. The agent retrieves an authorized relevant passage and cites it
  2. The agent selects the expected tool for a supported test query
  3. An out-of-scope request is handled under the approved restrictions
  4. An echo-free test response correctly addresses the supplied question

Explanation

Correct Answer

B:

A single agent can orchestrate a bounded tool without a multi-agent system. The expected acceptance evidence is: The agent selects the expected tool for a supported test query. This observation directly tests the stated behavior.

Incorrect Answers

A:

Tool descriptions guide selection, while backend rules enforce allowed sources. This observation does not establish the required result: The agent selects the expected tool for a supported test query.

C:

High-priority instructions should describe approved behavior and escalation rules. This observation does not establish the required result: The agent selects the expected tool for a supported test query.

D:

The inference service needs task content to generate a relevant answer. This observation does not establish the required result: The agent selects the expected tool for a supported test query.

Question 648

The approved design action is: Use visual document extraction with appropriate field and confidence rules. Which test result would BEST establish that it worked?

  1. The summary retains core findings and avoids ungrounded claims
  2. The top ranked article matches the issue and is permitted for that customer
  3. Offer letters and payslips reach their respective schemas
  4. Totals, dates and merchant names match receipt evidence

Explanation

Correct Answer

D:

Images of receipts need OCR/layout extraction before typed business values. The expected acceptance evidence is: Totals, dates and merchant names match receipt evidence. This observation directly tests the stated behavior.

Incorrect Answers

A:

Summarization compresses content without independently validating missing facts. This observation does not establish the required result: Totals, dates and merchant names match receipt evidence.

B:

Recommendations rank candidate items rather than simply generating arbitrary titles. This observation does not establish the required result: Totals, dates and merchant names match receipt evidence.

C:

Classification selects the extraction process matching the document category. This observation does not establish the required result: Totals, dates and merchant names match receipt evidence.

Question 649

The approved design action is: Combine video frame analysis with temporal segmentation. Which test result would BEST establish that it worked?

  1. The summary retains core findings and avoids ungrounded claims
  2. The narrated explanation matches labeled chart features without inventing values
  3. The timeline marks arrival frames with appropriate timestamps
  4. An article yields correctly labeled organizations and products

Explanation

Correct Answer

C:

Video understanding retains order and time, unlike single-image tagging. The expected acceptance evidence is: The timeline marks arrival frames with appropriate timestamps. This observation directly tests the stated behavior.

Incorrect Answers

A:

Summarization compresses content without independently validating missing facts. This observation does not establish the required result: The timeline marks arrival frames with appropriate timestamps.

B:

Multimodal input can describe the graphic and speech output can read that description. This observation does not establish the required result: The timeline marks arrival frames with appropriate timestamps.

D:

NER locates and categorizes named entities in text. This observation does not establish the required result: The timeline marks arrival frames with appropriate timestamps.

Question 650

A project needs the following AI behavior: A city information bot occasionally confuses current regulations with archived copies. What should the designer implement?

  1. Restrict retrieval to effective approved documents and expose source dates
  2. Evaluate outcomes with counterfactual name swaps and remove unjustified proxy effects
  3. Represent uncertainty explicitly and refer to approved teaching sources
  4. Assign accountable operational and risk owners with escalation responsibilities

Explanation

Correct Answer

A:

Truthfulness requires evidence that corresponds to the operative version. This implementation addresses the precise goal rather than an adjacent AI task.

Incorrect Answers

B:

Fairness checks compare materially equivalent cases rather than raw group averages alone. That is not sufficient here: Truthfulness requires evidence that corresponds to the operative version.

C:

Honesty requires acknowledging when a claim cannot be substantiated. That is not sufficient here: Truthfulness requires evidence that corresponds to the operative version.

D:

An AI model cannot be its own accountable incident responder. That is not sufficient here: Truthfulness requires evidence that corresponds to the operative version.

Microsoft Azure AI Fundamentals (AI-901) Practice Tests