- A
Use few-shot prompting with examples of desired clause extraction
Few-shot examples guide the model to produce consistent, structured outputs.
- B
Implement a human-in-the-loop review process for extracted clauses
Human review ensures accuracy and builds trust before moving to production.
- C
Test on a diverse set of 50-100 contracts covering common variations
A representative sample helps evaluate performance across formats without overwhelming the PoC.
- D
Deploy a pre-built contract analysis API without customization
Why wrong: Pre-built APIs may not handle the firm's specific contract language; customization is needed.
- E
Train a custom model from scratch using all historical contracts
Why wrong: Training from scratch is expensive and time-consuming; a PoC should use fine-tuning or prompt engineering first.
Generative AI Leader Applying Generative AI in Business Practice Question
This Generative AI Leader practice question tests your understanding of applying generative ai in business. Read the scenario carefully and evaluate each option against the stated constraints before committing to an answer. 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 law firm wants to use generative AI to analyze contracts and extract key clauses. They need high accuracy and the ability to handle diverse contract formats. Which three steps should they take in their proof-of-concept (PoC) phase? (Choose THREE)
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
Use few-shot prompting with examples of desired clause extraction
Few-shot prompting provides the model with specific examples of desired clause extraction, guiding it to produce accurate outputs without requiring fine-tuning. This technique is efficient for a proof-of-concept because it leverages the model's existing capabilities while adapting to the task through in-context learning, which is critical for handling diverse contract formats with high accuracy.
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.
- ✓
Use few-shot prompting with examples of desired clause extraction
Why this is correct
Few-shot examples guide the model to produce consistent, structured outputs.
Related concept
Read the scenario before looking for a memorised answer.
- ✓
Implement a human-in-the-loop review process for extracted clauses
Why this is correct
Human review ensures accuracy and builds trust before moving to production.
Related concept
Read the scenario before looking for a memorised answer.
- ✓
Test on a diverse set of 50-100 contracts covering common variations
Why this is correct
A representative sample helps evaluate performance across formats without overwhelming the PoC.
Related concept
Read the scenario before looking for a memorised answer.
- ✗
Deploy a pre-built contract analysis API without customization
Why it's wrong here
Pre-built APIs may not handle the firm's specific contract language; customization is needed.
- ✗
Train a custom model from scratch using all historical contracts
Why it's wrong here
Training from scratch is expensive and time-consuming; a PoC should use fine-tuning or prompt engineering first.
Common exam traps
Common exam trap: answer the scenario, not the keyword
Cisco often tests the misconception that a proof-of-concept should aim for a production-ready solution immediately, leading candidates to choose options like D (pre-built API) or E (custom training) instead of focusing on iterative, low-cost validation steps like few-shot prompting and human review.
Detailed technical explanation
How to think about this question
Few-shot prompting works by embedding example input-output pairs directly into the prompt context, leveraging the model's attention mechanism to infer the extraction pattern. In practice, the number of examples (typically 3-5) must be chosen carefully to avoid exceeding the model's context window (e.g., 4,096 tokens for GPT-3.5) while ensuring diversity to cover clause variations. A real-world scenario might involve extracting 'indemnification' clauses from contracts where the phrasing differs (e.g., 'hold harmless' vs. 'indemnify'), requiring examples that span these linguistic variants.
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.
- →
Applying Generative AI in Business — study guide chapter
Learn the concepts, then practise the questions
- →
Applying Generative AI in Business practice questions
Targeted practice on this topic area only
- →
All Generative AI Leader questions
997 questions across all exam domains
- →
Google Cloud Generative AI Leader Generative AI Leader study guide
Full concept coverage aligned to exam objectives
- →
Generative AI Leader practice test guide
How to use practice tests most effectively before exam day
Related practice questions
Related Generative AI Leader practice-question pages
Use these pages to review the topic behind this question. This is how one missed question becomes focused revision.
Fundamentals of Generative AI practice questions
Practise Generative AI Leader questions linked to Fundamentals of Generative AI.
Business Strategies for Generative AI Solutions practice questions
Practise Generative AI Leader questions linked to Business Strategies for Generative AI Solutions.
Generative AI Concepts and Technologies practice questions
Practise Generative AI Leader questions linked to Generative AI Concepts and Technologies.
Google AI Ecosystem and Strategy practice questions
Practise Generative AI Leader questions linked to Google AI Ecosystem and Strategy.
Responsible AI and Data Governance practice questions
Practise Generative AI Leader questions linked to Responsible AI and Data Governance.
Google Cloud's Generative AI Offerings practice questions
Practise Generative AI Leader questions linked to Google Cloud's Generative AI Offerings.
Techniques to Improve Generative AI Model Output practice questions
Practise Generative AI Leader questions linked to Techniques to Improve Generative AI Model Output.
Applying Generative AI in Business practice questions
Practise Generative AI Leader questions linked to Applying Generative AI in Business.
Generative AI Leader fundamentals practice questions
Practise Generative AI Leader questions linked to Generative AI Leader fundamentals.
Generative AI Leader scenario practice questions
Practise Generative AI Leader questions linked to Generative AI Leader scenario.
Generative AI Leader troubleshooting practice questions
Practise Generative AI Leader questions linked to Generative AI Leader troubleshooting.
Practice this exam
Start a free Generative AI Leader practice session
Short sessions build daily habit. Longer sessions build exam-day stamina. Try a timed session to simulate real conditions.
FAQ
Questions learners often ask
What does this Generative AI Leader question test?
Applying Generative AI in Business — This question tests Applying Generative AI in Business — Read the scenario before looking for a memorised answer..
What is the correct answer to this question?
The correct answer is: Use few-shot prompting with examples of desired clause extraction — Few-shot prompting provides the model with specific examples of desired clause extraction, guiding it to produce accurate outputs without requiring fine-tuning. This technique is efficient for a proof-of-concept because it leverages the model's existing capabilities while adapting to the task through in-context learning, which is critical for handling diverse contract formats with high accuracy.
What should I do if I get this Generative AI Leader question wrong?
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
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 →
Last reviewed: Jul 4, 2026
This Generative AI Leader practice question is part of Courseiva's free Google Cloud 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 Generative AI Leader 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.