🔒 Guided

Pre-launch preview. Authorised access only.

Incorrect code

Guided by A Guide to Cloud
Explore AB-900 AI-901
Guided AB-731 Domain 1
Domain 1 — Module 5 of 11 45%
5 of 27 overall

AB-731 Study Guide

Domain 1: Identify the Business Value of Generative AI Solutions

  • Generative AI vs Traditional AI: What's the Difference?
  • Choosing the Right AI Solution for Your Business
  • AI Models: Pretrained vs Fine-Tuned
  • AI Cost Drivers and ROI: Tokens, Pricing, and Business Cases
  • Challenges of Generative AI: Fabrications, Bias & Reliability
  • When Generative AI Creates Real Business Value
  • Prompt Engineering: The Skill That Multiplies AI Value
  • RAG and Grounding: Making AI Use YOUR Data
  • Data Quality: The Make-or-Break Factor for AI
  • When Traditional Machine Learning Adds Value
  • Securing AI Systems: From Application to Data

Domain 2: Identify Benefits, Capabilities, and Opportunities for Microsoft AI Apps and Services

  • Mapping Business Needs to Microsoft AI Solutions
  • Copilot Versions: Free, Business, M365, and Beyond
  • Copilot Chat: Web, Mobile & Work Experiences
  • Copilot in M365 Apps: Word, Excel, Teams & More
  • Copilot Studio & Microsoft Graph: Building Smarter Solutions
  • Researcher & Analyst: Copilot's Power Agents
  • Build, Buy, or Extend: The AI Decision Framework
  • Microsoft Foundry: Your AI Platform
  • Azure AI Services: Vision, Search & Beyond
  • Matching the Right AI Model to Your Business Need

Domain 3: Identify an Implementation and Adoption Strategy

  • Responsible AI and Governance: Principles That Protect Your Business Free
  • Setting Up an AI Council: Strategy, Oversight & Alignment Free
  • Building Your AI Adoption Team Free
  • AI Champions: Your Secret Weapon for Adoption Free
  • Data, Security, Privacy & Cost: The Four Pillars of AI Readiness Free
  • Copilot & Azure AI Licensing: Every Option Explained Free

AB-731 Study Guide

Domain 1: Identify the Business Value of Generative AI Solutions

  • Generative AI vs Traditional AI: What's the Difference?
  • Choosing the Right AI Solution for Your Business
  • AI Models: Pretrained vs Fine-Tuned
  • AI Cost Drivers and ROI: Tokens, Pricing, and Business Cases
  • Challenges of Generative AI: Fabrications, Bias & Reliability
  • When Generative AI Creates Real Business Value
  • Prompt Engineering: The Skill That Multiplies AI Value
  • RAG and Grounding: Making AI Use YOUR Data
  • Data Quality: The Make-or-Break Factor for AI
  • When Traditional Machine Learning Adds Value
  • Securing AI Systems: From Application to Data

Domain 2: Identify Benefits, Capabilities, and Opportunities for Microsoft AI Apps and Services

  • Mapping Business Needs to Microsoft AI Solutions
  • Copilot Versions: Free, Business, M365, and Beyond
  • Copilot Chat: Web, Mobile & Work Experiences
  • Copilot in M365 Apps: Word, Excel, Teams & More
  • Copilot Studio & Microsoft Graph: Building Smarter Solutions
  • Researcher & Analyst: Copilot's Power Agents
  • Build, Buy, or Extend: The AI Decision Framework
  • Microsoft Foundry: Your AI Platform
  • Azure AI Services: Vision, Search & Beyond
  • Matching the Right AI Model to Your Business Need

Domain 3: Identify an Implementation and Adoption Strategy

  • Responsible AI and Governance: Principles That Protect Your Business Free
  • Setting Up an AI Council: Strategy, Oversight & Alignment Free
  • Building Your AI Adoption Team Free
  • AI Champions: Your Secret Weapon for Adoption Free
  • Data, Security, Privacy & Cost: The Four Pillars of AI Readiness Free
  • Copilot & Azure AI Licensing: Every Option Explained Free
Domain 1: Identify the Business Value of Generative AI Solutions Premium ⏱ ~12 min read

Challenges of Generative AI: Fabrications, Bias & Reliability

Generative AI is powerful but not perfect. Leaders need to understand hallucinations, bias, reliability limitations, and how to mitigate these risks before deploying AI at scale.

Why generative AI isn’t magic

☕ Simple explanation

Generative AI is like a very confident intern — brilliant, fast, but sometimes wrong and never admits it.

It doesn’t actually “know” things. It predicts what text should come next based on patterns it learned during training. Most of the time, this produces great results. But sometimes it confidently states things that are completely wrong — and it does it with the same tone as when it’s right.

As a leader, you don’t need to fear these challenges — you need to understand them so you can deploy AI responsibly and set the right expectations.

Generative AI has inherent limitations that arise from its architecture and training process:

  • Fabrications (hallucinations): The model generates plausible-sounding but factually incorrect content because it’s predicting probable text sequences, not retrieving verified facts.
  • Bias: Models inherit biases from their training data. If the data over-represents certain perspectives, the model’s outputs will reflect those skews.
  • Reliability: The same prompt can produce different outputs each time (non-deterministic behaviour). Quality varies with prompt design and context.
  • Knowledge cutoff: Pretrained models have a training data cutoff date and don’t know about events after that date unless grounded with current data.

These aren’t defects — they’re characteristics of how the technology works. Mitigation strategies exist for each challenge.

The three big challenges

1. Fabrications (hallucinations)

The AI generates content that sounds correct but is factually wrong. It doesn’t “lie” — it’s predicting likely text sequences, and sometimes those predictions land on fiction.

What HappensReal-World ExampleRisk Level
Invents factsAI claims a regulation exists that doesn’tHigh — legal or compliance exposure
Creates fake sourcesCites a study or URL that doesn’t existMedium — credibility damage
Mixes real and fakeAccurate summary with one invented statisticHigh — hard to detect, easy to trust
Contradicts itselfSays “yes” in paragraph 1, “no” in paragraph 3Low — usually caught by careful readers

Mitigation strategies:

  • Grounding with RAG — connect the model to verified data sources
  • Human-in-the-loop — always review AI output before publishing or acting
  • Confidence thresholds — configure systems to flag low-confidence outputs
  • Citations — require the AI to cite sources so they can be verified

2. Bias

AI models learn from data that reflects human society — including its biases. The output can perpetuate or amplify unfair patterns.

Bias TypeHow It Shows UpExample
Training data biasModel over-represents certain demographics in its training dataAI writing job descriptions uses gendered language
Representation biasCertain groups are underrepresented in training dataAI performs poorly on accents from underrepresented regions
Confirmation biasModel reinforces the perspective of the promptAsk “why is X a problem?” and AI generates only negative content
Selection biasData used for RAG or fine-tuning has gapsCustomer service AI trained only on English queries fails for multilingual users

Mitigation strategies:

  • Diverse, representative datasets — for fine-tuning and RAG
  • Regular bias audits — test outputs across different demographics
  • Content filters — block harmful or inappropriate output
  • Transparency — tell users when they’re interacting with AI

3. Reliability

Generative AI is probabilistic, not deterministic. The same prompt can produce different outputs each time.

Reliability ChallengeBusiness ImpactMitigation
Non-deterministic outputHard to guarantee consistent qualityUse temperature settings, structured prompts, and output validation
Prompt sensitivitySmall wording changes produce very different resultsDevelop and test standard prompts for critical workflows
Context limitationsLong documents may be summarised inconsistentlyBreak large inputs into chunks, use structured prompts
Model degradationPerformance can change when models are updatedPin model versions for critical applications, test after updates
💡 Scenario: Dr. Patel's board briefing on AI risks

Dr. Anisha Patel (board advisor) prepares a risk briefing for a healthcare company evaluating generative AI:

Red flags she raises:

  • Fabrications in medical AI could lead to patient harm and regulatory violations
  • Bias in diagnostic AI could mean unequal treatment across patient demographics
  • Reliability issues in automated clinical notes could create legal liability

Her recommendation: Deploy AI with human-in-the-loop validation for all clinical applications. Use AI for administrative tasks (scheduling, summarisation) where hallucination risk is lower before expanding to clinical decision support.

Other challenges leaders face

Beyond the “big three,” business leaders should also be aware of:

ChallengeWhat It MeansBusiness Impact
Data privacyAI may process sensitive data and leak it in outputsMust enforce data boundaries and access controls
Intellectual propertyAI trained on copyrighted material raises IP questionsLegal risk when generating content that resembles copyrighted works
Over-relianceUsers trust AI too much and stop thinking criticallyQuality degrades as humans skip verification
Shadow AIEmployees use unapproved AI toolsData leaks, compliance violations, security gaps
ExplainabilityAI can’t explain WHY it generated a specific outputHard to audit or defend AI-driven decisions
💡 Exam tip: Fabrications vs hallucinations

Microsoft uses the term “fabrications” in the official exam skills outline (not “hallucinations”). Both terms refer to the same thing — AI generating false content confidently. Use “fabrications” in your exam answers to match Microsoft’s terminology.

Turning challenges into governance opportunities

Smart leaders don’t avoid AI because of these challenges — they build governance frameworks to manage them:

  1. Establish acceptable use policies — define where AI can and can’t be used
  2. Require human review for high-stakes outputs (legal, medical, financial)
  3. Implement content filters — Microsoft’s content safety tools block harmful outputs
  4. Monitor and audit — track AI usage patterns and output quality
  5. Train users — help them understand AI limitations and verify outputs

Key flashcards

Question

What is an AI 'fabrication' (hallucination)?

Click or press Enter to reveal answer

Answer

When an AI model generates content that sounds plausible and confident but is factually incorrect. It happens because the model predicts likely text sequences, not verified facts.

Click to flip back

Question

What are the three main types of bias in AI?

Click or press Enter to reveal answer

Answer

1. Training data bias (data over-represents certain groups). 2. Representation bias (certain groups are underrepresented). 3. Selection bias (data used for grounding or fine-tuning has gaps).

Click to flip back

Question

Why is generative AI 'unreliable' compared to traditional software?

Click or press Enter to reveal answer

Answer

Generative AI is probabilistic (non-deterministic) — the same prompt can produce different outputs each time. Traditional software is deterministic — same input always produces the same output.

Click to flip back

Question

What is the most effective way to reduce AI fabrications?

Click or press Enter to reveal answer

Answer

Grounding with RAG (Retrieval-Augmented Generation) — connecting the model to verified data sources so it answers from YOUR trusted data, not just its training knowledge.

Click to flip back

Knowledge check

Knowledge Check

Elena's consulting firm deploys Copilot for drafting client proposals. A consultant submits a proposal that cites a regulation that doesn't actually exist. What type of AI challenge is this?

Knowledge Check

Tomás notices that the AI writing job descriptions at PacificSteel consistently uses masculine language. What type of challenge is this, and what should he do?

Knowledge Check

Dr. Patel recommends that a healthcare company deploy AI for administrative tasks before clinical applications. What is the primary reason for this phased approach?

🎬 Video coming soon

Next up: When Generative AI Creates Real Business Value — scalability, automation, and the scenarios where AI delivers transformative impact.

← Previous

AI Cost Drivers and ROI: Tokens, Pricing, and Business Cases

Next →

When Generative AI Creates Real Business Value

Guided

I learn, I simplify, I share.

A Guide to Cloud YouTube Feedback

© 2026 Sutheesh. All rights reserved.

Guided is an independent study resource and is not affiliated with, endorsed by, or officially connected to Microsoft. Microsoft, Azure, and related trademarks are property of Microsoft Corporation. Always verify information against Microsoft Learn.