What is Chain-of-Thought Prompting?
What is 'chain-of-thought prompting' and when is it most effective?
Quick Answer
The correct answer is prompting the model to show explicit reasoning steps before giving a final answer. This technique, known as chain-of-thought prompting, works by instructing the AI to break down a complex problem into intermediate, logical steps rather than jumping straight to a conclusion, which mirrors how a human might solve a multi-step math problem or a logic puzzle. On the Microsoft Azure AI Fundamentals AI-900 exam, this concept tests your understanding of how to improve model accuracy for tasks requiring multi-step reasoning, such as arithmetic or commonsense inference, and it often appears as a scenario where you need to choose the method that reduces shortcut errors. A common trap is confusing it with simple zero-shot prompting, which lacks the step-by-step structure. Memory tip: think of it as “show your work” for AI—just like a math teacher wants to see each step, chain-of-thought prompting forces the model to reveal its reasoning before the final answer.
⚠ Common exam trap
It's easy for candidates to confuse 'chain-of-thought prompting' with 'model chaining' or 'pipeline architectures' (Option A), because both involve a sequence, but chain-of-thought is a single-model prompting technique, not a multi-model workflow.
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
✓
Prompting the model to show explicit reasoning steps before giving a final answer
Chain-of-thought prompting instructs the model to break down a complex problem into intermediate reasoning steps before producing the final answer. This technique improves accuracy on tasks requiring multi-step logic, such as arithmetic, commonsense reasoning, or symbolic manipulation, by making the model's internal reasoning explicit and reducing errors from shortcut answers.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Linking multiple AI models in a pipeline where each model's output feeds the next
Why it's wrong here
Model chaining is an AI architecture pattern — chain-of-thought is a single-model prompting technique for eliciting explicit reasoning.
- ✓
Prompting the model to show explicit reasoning steps before giving a final answer
Why this is correct
CoT prompting ('think step by step') improves multi-step reasoning by externalising the reasoning process — most effective for maths and logic.
- ✗
Training a model on a sequence of related documents to build contextual knowledge
Why it's wrong here
Sequential document training is fine-tuning — CoT is an inference-time prompting technique requiring no model changes.
- ✗
A method for connecting chatbot conversation turns to maintain long-term memory
Why it's wrong here
Long-term memory is a conversational AI architecture concern — CoT is a prompting strategy for improving step-by-step reasoning.
Go deeper
Related to this question
About these practice questions
Courseiva writes every AI-900 question from scratch — 985 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. Learn why practice questions differ from exam dumps →
Same concept, more angles
1 more way this is tested on AI-900
These questions test the same concept from different angles. Work through them to make sure you can recognise it however the exam phrases it.
Variation 1. What is 'chain of thought' prompting in generative AI?
medium- A.Connecting multiple AI models in a processing pipeline
- ✓ B.A prompting technique that elicits step-by-step reasoning to improve accuracy on complex tasks
- C.Linking multiple conversation turns to maintain context
- D.Training a model using sequential text data only
Why B: Chain of thought prompting is a technique where the model is asked to produce intermediate reasoning steps before arriving at a final answer, which significantly improves performance on multi-step arithmetic, logic, and common-sense reasoning tasks. Unlike a simple answer request, it forces the model to externalize its reasoning process, reducing errors from shortcut or pattern-matching behaviors. This is a prompting strategy, not a model architecture change, and is particularly effective in large language models like GPT-4 or Azure OpenAI's GPT-3.5 Turbo.
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This AI-900 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 AI-900 exam.