The answer is that invoices are sent to manual review because the AI Builder model’s confidence score for extracted fields falls below the configured threshold of 0.8. In the JSON configuration, this threshold acts as a quality gate: when the model’s prediction certainty for any field drops under 0.8, the system automatically routes the invoice for human verification rather than accepting low-confidence data. On the Microsoft Dynamics 365 Fundamentals ERP MB-920 exam, this scenario tests your understanding of how AI Builder balances automation with accuracy in invoice processing—a common trap is assuming manual review only happens for missing data, when in fact it’s triggered by low confidence scores. Remember the keyword “threshold” as the gatekeeper: if confidence dips below the line, manual review is the default safety net. A simple memory tip: “Below 0.8? Time for a human to verify.”
MB-920 Practice Question: Describe shared features and Copilot capabilities
This MB-920 practice question tests your understanding of describe shared features and copilot capabilities. This is a configuration task: choose the command set that satisfies every stated requirement. Small differences — like 'secret' vs 'password' or 'transport input ssh' vs 'all' — change whether the answer is correct. After answering, compare your reasoning against the explanation and wrong-answer breakdown below. Once you have made your selection, read the full explanation to reinforce the concept and understand why each distractor is designed to mislead on exam day.
A Dynamics 365 Finance administrator configures an AI Builder model for invoice processing with the above JSON. After deployment, the system correctly extracts data from 90% of invoices but sends 10% to manual review. What is the most likely reason for the manual review?
Clue words in this question
Noticing these words before you look at the options changes how you read each choice.
Clue: "most likely"
Why it matters: Probability qualifier — the question wants the most probable cause or outcome, not a guaranteed one. Eliminate low-probability options.
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
The confidence score for extracted fields is below the threshold of 0.8 for those invoices
The JSON configuration sets a confidence threshold of 0.8 for extracted fields. When the model's confidence in the extracted data falls below this threshold, the system automatically routes the invoice to manual review. This is the standard behavior for AI Builder invoice processing models to ensure accuracy and reduce errors from low-confidence predictions.
Key principle: Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
✗
The invoice images are too blurry for the model to read
Why it's wrong here
While blurry images could reduce confidence, the manual review is triggered by confidence threshold, not directly by blur.
✓
The confidence score for extracted fields is below the threshold of 0.8 for those invoices
Why this is correct
Exactly: the model's confidence is below 0.8, triggering the fallback action.
Clue confirmation
The clue word "most likely" in the question point toward this answer.
Related concept
Read the scenario before looking for a memorised answer.
✗
The model extracts all fields but with confidence below 0.9
Why it's wrong here
The threshold is 0.8, not 0.9; below 0.8 triggers manual review.
✗
The invoice contains multiple pages that need to be split
Why it's wrong here
The exhibit does not mention split; fallback is manual review, not splitting.
Common exam traps
Common exam trap: answer the scenario, not the keyword
The trap here is that candidates may assume the threshold is 0.9 (option C) because it is a common default in some AI models, but the JSON explicitly shows 0.8, and the question tests attention to the configuration details.
Detailed technical explanation
How to think about this question
AI Builder invoice processing models use a confidence score (0 to 1) for each extracted field, and the threshold parameter in the JSON defines the minimum acceptable confidence. When any field's confidence is below this threshold, the entire document is flagged for manual review. In real-world scenarios, this threshold is often set to 0.8 to balance automation rate and accuracy, as lower thresholds increase false positives while higher thresholds reduce automation.
KKey Concepts to Remember
Read the scenario before looking for a memorised answer.
Find the constraint that changes the correct option.
Eliminate answers that are true in general but not in this case.
TExam Day Tips
→Watch for words such as best, first, most likely and least administrative effort.
→Review why wrong options are wrong, not only why the correct option is correct.
Key takeaway
Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Real-world example
How this comes up in practice
A cloud solutions architect for a retail company is evaluating services for a new workload. The correct answer here reflects best practice for the specific scenario described — not a general cloud recommendation. Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option. Cloud exam questions reward reading the constraint carefully: the same technology can be right or wrong depending on the use case.
What to study next
Got this wrong? Here's your next step.
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
Describe shared features and Copilot capabilities — This question tests Describe shared features and Copilot capabilities — Read the scenario before looking for a memorised answer..
What is the correct answer to this question?
The correct answer is: The confidence score for extracted fields is below the threshold of 0.8 for those invoices — The JSON configuration sets a confidence threshold of 0.8 for extracted fields. When the model's confidence in the extracted data falls below this threshold, the system automatically routes the invoice to manual review. This is the standard behavior for AI Builder invoice processing models to ensure accuracy and reduce errors from low-confidence predictions.
What should I do if I get this MB-920 question wrong?
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
Are there clue words in this question I should notice?
Yes — watch for: "most likely". Probability qualifier — the question wants the most probable cause or outcome, not a guaranteed one. Eliminate low-probability options.
What is the key concept behind this question?
Read the scenario before looking for a memorised answer.
About these practice questions
Courseiva creates original exam-style practice questions with explanations and wrong-answer analysis. It does not publish real exam questions, exam dumps, or protected exam content. Learn why practice questions differ from exam dumps →
Share a tip, memory trick, or ask about the reasoning behind this question. Do not post real exam questions, leaked content, braindumps, or copyrighted exam material. Comments are moderated and may be removed without notice.
This MB-920 practice question is part of Courseiva's free Microsoft certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the MB-920 exam.
Question Discussion
Share a tip, memory trick, or ask about the reasoning behind this question. Do not post real exam questions, leaked content, braindumps, or copyrighted exam material. Comments are moderated and may be removed without notice.
Sign in to join the discussion.