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 89

Question 880

Troubleshooting report: The tool performs sentiment classification instead of translation. Which correction is MOST directly targeted to this failure?

  1. Pass supported audio content to an audio-capable model
  2. Require source-attributed action extraction
  3. Select the correct source/target language translation path
  4. Load the deployed speech resource's region and endpoint

Explanation

Correct Answer

C:

This correction directly addresses the reported failure. Translation requires semantic equivalence and language direction. The targeted change is: Select the correct source/target language translation path.

Incorrect Answers

A:

A text-only request cannot interpret sound content by file name alone. In the stated case, troubleshooting report: The tool performs sentiment classification instead of translation; “Pass supported audio content to an audio-capable model” does not target that failure.

B:

Transcription obtains words; summarization extracts decisions and tasks. In the stated case, troubleshooting report: The tool performs sentiment classification instead of translation; “Require source-attributed action extraction” does not target that failure.

D:

Region or endpoint mismatch prevents requests reaching the correct resource. In the stated case, troubleshooting report: The tool performs sentiment classification instead of translation; “Load the deployed speech resource's region and endpoint” does not target that failure.

Question 881

An Azure AI Fundamentals solution has this requirement: A model can process a speech clip and return words. Which implementation most directly addresses it?

  1. Choose a compatible multimodal model and provide supported text/image inputs
  2. Confirm the model deployment identifier and endpoint resource match
  3. Choose a speech-recognition model or audio-capable multimodal endpoint with a documented audio-input contract
  4. Measure expected tokens and requests per minute, then choose an approved throughput tier or capacity adjustment before launch

Explanation

Correct Answer

C:

Model capabilities must include the required audio modality before the client can obtain speech-to-text results.

Incorrect Answers

A:

Multimodal models can reason over more than one supported input modality. That is not sufficient here: Model capabilities must include the required audio modality before the client can obtain speech-to-text results.

B:

Applications call a deployed model resource rather than a generic marketing model name. That is not sufficient here: Model capabilities must include the required audio modality before the client can obtain speech-to-text results.

D:

Quota sizing is a deployment-capacity decision; retrying a predictable sustained excess cannot add model throughput. That is not sufficient here: Model capabilities must include the required audio modality before the client can obtain speech-to-text results.

Question 882

An engineering review documents this requirement: A document extraction job includes pages in multiple languages. Select the most appropriate solution.

  1. Use supported locale-aware OCR or language handling with evaluation
  2. Enable a supported barcode extraction or recognition feature
  3. Define schema fields for document date, due date and signature date
  4. Apply confidence-based review instead of forcing every field into a number

Explanation

Correct Answer

A:

Recognition accuracy depends on script and language support. This implementation addresses the precise goal rather than an adjacent AI task.

Incorrect Answers

B:

A barcode is a structured visual symbol not ordinary OCR text. That is not sufficient here: Recognition accuracy depends on script and language support.

C:

Typed extraction avoids mixing semantically different dates. That is not sufficient here: Recognition accuracy depends on script and language support.

D:

Low-quality inputs can make extraction genuinely uncertain. That is not sufficient here: Recognition accuracy depends on script and language support.

Question 883

Troubleshooting report: The only disclosure is buried in an administrator-only configuration page. Which correction is MOST directly targeted to this failure?

  1. Scope the token and backend authorization to necessary actions
  2. Require a data query or report unavailability
  3. Expand the consented voice test corpus and provide fallback interaction
  4. Surface the notice in the actual user interaction flow

Explanation

Correct Answer

D:

This correction directly addresses the reported failure. Transparency helps users assess the scope and limitations of the assistance. The targeted change is: Surface the notice in the actual user interaction flow.

Incorrect Answers

A:

Least privilege reduces damage from compromised prompts or tool output. In the stated case, troubleshooting report: The only disclosure is buried in an administrator-only configuration page; “Scope the token and backend authorization to necessary actions” does not target that failure.

B:

A numeric-looking answer is not proof that a measure was computed. In the stated case, troubleshooting report: The only disclosure is buried in an administrator-only configuration page; “Require a data query or report unavailability” does not target that failure.

C:

Inclusive voice systems require performance evaluation beyond a single accent. In the stated case, troubleshooting report: The only disclosure is buried in an administrator-only configuration page; “Expand the consented voice test corpus and provide fallback interaction” does not target that failure.

Question 884

An Azure AI Fundamentals solution has this requirement: A retailer wants to identify whether a product is present in a shelf photo. Which implementation most directly addresses it?

  1. Use PII-aware entity recognition with appropriate redaction
  2. Use noise-aware speech recognition and intent classification with fallback
  3. Use object detection when each product needs a location
  4. Use invoice-oriented structured extraction with table row preservation

Explanation

Correct Answer

C:

Object detectors return classes and spatial boundaries. This implementation addresses the precise goal rather than an adjacent AI task.

Incorrect Answers

A:

Entity extraction locates sensitive spans for privacy handling. That is not sufficient here: Object detectors return classes and spatial boundaries.

B:

Speech input quality affects subsequent language classification. That is not sufficient here: Object detectors return classes and spatial boundaries.

D:

Table extraction associates quantities, descriptions and prices by row. That is not sufficient here: Object detectors return classes and spatial boundaries.

Question 885

Troubleshooting report: The app acts on an unconfirmed low-confidence numeral. Which correction is MOST directly targeted to this failure?

  1. Send valid audio to a speech recognition endpoint
  2. Adjust recognition vocabulary and test the target terms
  3. Apply a confirmation prompt and constrained recognition
  4. Add a no-speech branch and clarification option

Explanation

Correct Answer

C:

This correction directly addresses the reported failure. Speech recognition uncertainty is higher for confusable numeric strings. The targeted change is: Apply a confirmation prompt and constrained recognition.

Incorrect Answers

A:

Speech recognition converts waveform features to text tokens. In the stated case, troubleshooting report: The app acts on an unconfirmed low-confidence numeral; “Send valid audio to a speech recognition endpoint” does not target that failure.

B:

Domain-specific words may require biasing or adaptation beyond a generic recognizer. In the stated case, troubleshooting report: The app acts on an unconfirmed low-confidence numeral; “Adjust recognition vocabulary and test the target terms” does not target that failure.

D:

An empty recognition result is not semantically equivalent to the word no. In the stated case, troubleshooting report: The app acts on an unconfirmed low-confidence numeral; “Add a no-speech branch and clarification option” does not target that failure.

Question 886

A solution team has selected this control: Check actual tool execution results before reporting the outcome. Which observation is the most direct acceptance evidence?

  1. A smoke test reaches the intended new deployment and parses the output
  2. The response cites a completed tool receipt and actual returned data
  3. The answer mentions relevant visual details unique to the uploaded image
  4. Injection attempts fail to access protected secrets or tools

Explanation

Correct Answer

B:

Generated text does not prove external execution. The expected acceptance evidence is: The response cites a completed tool receipt and actual returned data. This observation directly tests the stated behavior.

Incorrect Answers

A:

A model family label is not necessarily the concrete deployed endpoint. This observation does not establish the required result: The response cites a completed tool receipt and actual returned data.

C:

The model must receive the actual visual content to reason about it. This observation does not establish the required result: The response cites a completed tool receipt and actual returned data.

D:

A user cannot use text to elevate permissions beyond the application policy. This observation does not establish the required result: The response cites a completed tool receipt and actual returned data.

Question 887

An acceptance tester needs to validate: Use text summarization with fidelity checks against sources. Which observed result proves the intended behavior?

  1. Answers cite valid manual passages and avoid unsupported details
  2. The spoken message matches the approved written text
  3. The summary preserves the topic sequence and supported key points
  4. The summary retains core findings and avoids ungrounded claims

Explanation

Correct Answer

D:

Summarization compresses content without independently validating missing facts. The expected acceptance evidence is: The summary retains core findings and avoids ungrounded claims. This observation directly tests the stated behavior.

Incorrect Answers

A:

RAG retrieves current external evidence for a generated response. This observation does not establish the required result: The summary retains core findings and avoids ungrounded claims.

B:

Speech synthesis converts supplied text into audible output. This observation does not establish the required result: The summary retains core findings and avoids ungrounded claims.

C:

Meeting summaries require temporal and spoken source content. This observation does not establish the required result: The summary retains core findings and avoids ungrounded claims.

Question 888

An acceptance tester needs to validate: Check supported context and output limits for the chosen deployment. Which observed result proves the intended behavior?

  1. A proposed snippet passes syntax and behavioral tests before merge
  2. The same authorized case ID is observed in every step receipt
  3. An authenticated test request returns a response from the chosen deployment
  4. A representative maximum-size test stays within documented budgets

Explanation

Correct Answer

D:

Capabilities and limits vary by model deployment. The expected acceptance evidence is: A representative maximum-size test stays within documented budgets. This observation directly tests the stated behavior.

Incorrect Answers

A:

Generated code must be validated, not treated as production-ready from fluency. This observation does not establish the required result: A representative maximum-size test stays within documented budgets.

B:

Structured state prevents subtle substitution of unrelated customer records. This observation does not establish the required result: A representative maximum-size test stays within documented budgets.

C:

The portal provides model selection, deployment and test interfaces for supported resources. This observation does not establish the required result: A representative maximum-size test stays within documented budgets.

Question 889

An acceptance tester needs to validate: Use a supported smart-crop feature with the requested aspect ratio. Which observed result proves the intended behavior?

  1. The count matches annotated packages after overlap filtering
  2. A reviewer can locate the source field in the image from its coordinates
  3. The result depicts the prompt without implying original photo preservation
  4. The crop keeps the subject in view at the specified aspect ratio

Explanation

Correct Answer

D:

Smart cropping attempts to retain salient regions within target dimensions. The expected acceptance evidence is: The crop keeps the subject in view at the specified aspect ratio. This observation directly tests the stated behavior.

Incorrect Answers

A:

Object counts require resolving distinct instances, not trusting one scene label. This observation does not establish the required result: The crop keeps the subject in view at the specified aspect ratio.

B:

Spatial provenance supports later verification of recognition results. This observation does not establish the required result: The crop keeps the subject in view at the specified aspect ratio.

C:

Generation from text is distinct from image editing. This observation does not establish the required result: The crop keeps the subject in view at the specified aspect ratio.

Question 890

An acceptance tester needs to validate: Use speech-to-text transcription before indexing call content. Which observed result proves the intended behavior?

  1. Line-item totals and row relationships reconcile to the document
  2. Names in a labeled sample are detected and redacted
  3. Suggested products are relevant and meet inventory/authorization rules
  4. The transcript contains the actual spoken issue and timestamp

Explanation

Correct Answer

D:

Speech recognition converts speech into words suitable for search. The expected acceptance evidence is: The transcript contains the actual spoken issue and timestamp. This observation directly tests the stated behavior.

Incorrect Answers

A:

Table extraction associates quantities, descriptions and prices by row. This observation does not establish the required result: The transcript contains the actual spoken issue and timestamp.

B:

Entity extraction locates sensitive spans for privacy handling. This observation does not establish the required result: The transcript contains the actual spoken issue and timestamp.

C:

Semantic vectors capture related concepts while filters enforce eligibility. This observation does not establish the required result: The transcript contains the actual spoken issue and timestamp.

Microsoft Azure AI Fundamentals (AI-901) Practice Tests