AB-731

AI Transformation Leader AB-731 practice exams

240 questions in 5 timed practice tests. Each test has about 51 questions and a 100-minute limit. The pass mark is 70%. Results are split across the 3 exam domains.

Exam at a glance

AB-731 practice exam settings
Practice tests 5
Questions in total 240
Questions per test About 51
Time limit per test 100 minutes
Pass mark 70%
Question types Single answer and multiple answer (25 multiple-answer questions)
Level Foundational
Category AI & Machine Learning

These are the settings of our practice tests. Check the official Microsoft exam page for the current exam format before you book.

Domains and weights

AB-731 exam domains, weights and question counts
Domain Weight Weight bar Questions in our bank
Identify the business value of generative AI solutions 38% 91
Identify benefits, capabilities, and opportunities for Microsoft's AI apps and services 39% 94
Identify an implementation and adoption strategy for Microsoft's AI apps and services 23% 55

Sample questions

Question 1 of 3

A retail executive asks how generative AI differs from the predictive model the company already uses to forecast weekly store demand. Which statement BEST describes the difference?

  1. A Generative AI always returns the same output for the same input, while predictive forecasting models are designed to vary their answers on each run.
  2. B Generative AI only works with structured tabular data such as sales tables, while predictive models are designed to process unstructured documents, images, and audio.
  3. C Generative AI requires labeled training data for every output it produces, while predictive models learn entirely without any labeled examples.
  4. D Generative AI produces new content such as text, images, or code, while the forecasting model predicts a value or label from patterns in historical data. (correct answer)
Why: Generative AI creates new content (text, images, code, summaries) based on patterns learned during training, whereas traditional predictive models output a number or class such as next week's demand. Generative models are especially strong with unstructured data, not limited to tables. Foundation models are pretrained largely with self-supervised learning rather than labels for every output, and generative output is non-deterministic, so the other statements reverse the real characteristics.

Question 2 of 3

A legal operations team pilots a chat assistant that drafts summaries of contract clauses. Reviewers find that some summaries cite clauses that do not exist in the source contract. Which generative AI challenge does this describe, and what is the MOST appropriate first mitigation?

  1. A Fabrication; ground the assistant on the actual contract text and require clause citations that reviewers can check against the source. (correct answer)
  2. B Latency; move the assistant to a provisioned throughput deployment so that summaries are generated faster during the peak contract review hours.
  3. C Bias; retrain the underlying foundation model from scratch on a balanced set of contracts from many different jurisdictions.
  4. D Data drift; schedule monthly retraining of a classification model so that contract categories stay aligned with the current portfolio.
Why: Content that sounds plausible but is not supported by the source is a fabrication (often called a hallucination). Grounding the model on the real contract and showing citations lets humans verify every claim. Retraining a foundation model to fix bias is costly and does not address invented clauses, provisioned throughput affects speed and capacity rather than accuracy, and drift retraining applies to predictive models whose input data changes over time.

Question 3 of 3

A customer-support leader wants to reduce the cost of an AI assistant without hurting answer quality. Analysis shows that every request includes a 6,000-word policy manual pasted into the prompt. Which change would MOST reduce token consumption while keeping answers grounded?

  1. A Ask agents to rephrase each customer question more politely, because courteous prompts are processed with fewer tokens.
  2. B Index the manual and use retrieval so that only the few passages relevant to each question are added to the prompt. (correct answer)
  3. C Switch to a larger model with a bigger context window so the full manual fits more comfortably in every request.
  4. D Increase the maximum output length setting so the model can answer several customer questions inside one long response.
Why: Retrieval-augmented generation retrieves only the passages relevant to the question, which cuts input tokens dramatically while keeping responses grounded in the manual. A larger context window lets more text fit but does not reduce what you pay for, and larger models usually cost more per token. Politeness does not meaningfully change token counts, and raising the output limit increases rather than reduces consumption.

What your score report looks like

Example attempt, AB-731 practice test 3

83%

Passed
Pass mark 70%

Score by exam domain
DomainWeightYour score%
Identify the business value of generative AI solutions 38%
88
Identify benefits, capabilities, and opportunities for Microsoft's AI apps and services 39%
81
Identify an implementation and adoption strategy for Microsoft's AI apps and services 23%
76

Study next: Identify an implementation and adoption strategy for Microsoft's AI apps and services. It is below the pass mark and carries 23% of the exam.

Domains and pass mark from our AB-731 practice tests. Scores are an example attempt.

Study plans

Two weeks

  1. Day 1: take practice test 1 in exam mode to get a baseline.
  2. Days 2 to 5: domain mode on Identify benefits, capabilities, and opportunities for Microsoft's AI apps and services and Identify the business value of generative AI solutions, the two most heavily weighted domains.
  3. Day 6: practice test 2 in exam mode, then the mistakes quiz.
  4. Days 7 to 12: practice tests 3 to 5, one every other day, each followed by its mistakes quiz.
  5. Days 13 and 14: final mode. Book the exam when your readiness stays above the pass mark.

Four weeks

  1. Week 1: one practice test in practice mode, reading every explanation. Note your two lowest domains.
  2. Week 2: domain mode on those two domains, then a second practice test in exam mode.
  3. Week 3: practice tests 3 and 4 in exam mode, with the mistakes and flagged quizzes after each.
  4. Week 4: practice test 5 and final mode until your readiness holds above the pass mark.

Questions about the AB-731 practice exams

Are these real AB-731 exam questions?
No. We write every question ourselves and map it to the published AB-731 exam objectives. We do not use leaked or recalled questions.
Do the time limit and pass mark match the official exam?
They match the settings of our practice tests. Exam providers change their format from time to time, so check the official exam page before you book.
Can I try it before I pay?
Yes. The free mini exam has 15 questions with full explanations and needs no account.
How long do I keep access?
A single-exam purchase gives you 12 months of access. All-Access includes this exam for as long as your subscription runs.
What happens after I finish a test?
You get a score, a pass or fail against the pass mark, a score per domain and every answer with its explanation.

Last updated November 2026. Written and reviewed by the DevOpsCode Lab team.

DevOpsCode Lab is not affiliated with Microsoft. AB-731 and related names are trademarks of their owners.

Related exams
Exam Vendor Level Questions Minutes Price
AB-400Power Platform Developer AB-400 (formerly PL-400) Microsoft Associate 251 100 $12.99
AB-410AB-410 Building Intelligent Applications Microsoft Associate 250 100 $12.99
AB-620Copilot Studio AB-620 Microsoft Associate 251 100 $12.99
AI-103Azure AI Apps & Agents AI-103 Microsoft Associate 250 100 $12.99
AI-200Azure AI Cloud Developer AI-200 Microsoft Associate 250 100 $12.99
AI-300AI-300 ML and Generative AI Operations Microsoft Associate 251 100 $12.99