More Prompts:

Best prompts for ChatGPT using chain-of-thought elicitation

12 practical, copy-ready prompts that elicit step-by-step chain-of-thought reasoning for common tasks: math, coding, debugging, analysis, planning, legal/technical interpretation, and prompt engineering. Each entry includes a concise explanation, a realistic example, and recommended AIs that perform best with this style.

Claude Opus 4
GPT-5
Claude Sonnet 4
Gemini 2.5 Pro
Gemini 2.5 Flash
You know that sinking feeling when ChatGPT gives you a brilliant-sounding answer that turns out to be completely wrong? You're not alone in wondering whether the AI actually "thought" through the problem or just strung together convincing words. The truth is, most people are using AI like a magic 8-ball when they could be using it like a thinking partner.
This collection of 12 battle-tested prompts transforms how you interact with AI by forcing it to show its work step-by-step. From debugging code and solving math problems to analyzing legal clauses and planning projects, these chain-of-thought prompts turn AI responses from mysterious black boxes into transparent reasoning processes you can actually trust. Instead of crossing your fingers and hoping for accuracy, you'll get reliable, verifiable answers that walk you through every logical step.
1
Step-by-step arithmetic word problem solver
Read the word problem below. Show your chain-of-thought: enumerate each reasoning step, perform intermediate calculations explicitly, and then provide the final numeric answer in one short line. Do not omit steps. Problem: {problem_text}
Solve a word problem by showing each reasoning step, intermediate calculations, and a final concise answer.
2
Algebra derivation with explicit steps
Derive the result for the equation below. Provide a numbered, line-by-line chain-of-thought showing each algebraic step, the justification for that step, and the final simplified expression. Equation: {equation}
Request a full algebraic derivation: show manipulations line-by-line, justify each transformation, then state the simplified result.
3
Probability and Bayesian reasoning, stepwise
Compute the requested probability. Write a clear chain-of-thought: list assumptions, write formulas used, compute intermediate values explicitly, and end with a one-sentence interpretation of the final probability. Question: {probability_question}
Walk through probability computations (including Bayes' theorem) step-by-step, show intermediate probabilities, and give a final probability with interpretation.
4
Algorithm design with stepwise rationale and pseudocode
Design an algorithm for the task below. Provide a chain-of-thought that: (1) lists constraints and goals, (2) considers alternatives with pros/cons, (3) chooses an approach with justification, (4) gives step-by-step pseudocode, and (5) gives time/space complexity. Task: {task_description}
Elicit design choices and stepwise reasoning for an algorithm, then produce clear pseudocode and complexity analysis.
5
Code debugging with hypothesis-driven chain-of-thought
Here is a failing code snippet. Show your chain-of-thought: describe hypotheses for the bug, propose minimal tests to reproduce, run through the failing example with intermediate values (conceptually), identify the root cause, and provide a corrected code snippet with a brief explanation. Code: {code_snippet} Error/Behavior: {error_description}
Debug code by listing hypotheses, tests, reproducing failures, and showing stepwise fixes and final corrected snippet.
6
Data analysis interpretation with stepwise evidence
Analyze the dataset summary below. Provide a numbered chain-of-thought covering data cleaning assumptions, checks performed, statistical calculations with intermediate results, and end with a concise, actionable summary. Data summary: {data_summary_or_sample}
Analyze a small dataset: list cleaning steps, exploratory checks, statistical computations step-by-step, and conclude with actionable insights.
7
Legal-style clause application with step-by-step analysis
Analyze whether the rule below applies to the facts. Provide a chain-of-thought: (1) list rule elements, (2) map each fact to elements step-by-step, (3) note ambiguities and alternative interpretations, and (4) give a reasoned conclusion and a confidence estimate. Rule: {statute_or_rule} Facts: {facts}
Apply a legal rule to facts: list elements of the rule, map facts to elements stepwise, discuss any ambiguous points, and conclude with a reasoned outcome and confidence level.
AI Flow Chat

Stop Losing Your AI Work

Tired of rewriting the same prompts, juggling ChatGPT and Claude in multiple tabs, and watching your best AI conversations disappear forever?

AI Flow Chat lets you save winning prompts to a reusable library, test all models in one workspace, and convert great chats into automated workflows that scale.

Teach World Class AI About Your Business, Content, Competitors… Get World Class Answers, Content, Suggestions...
AI Flow Chat powers our entire content strategy. We double down on what’s working, extract viral elements, and create stuff fast.
Video thumbnail

Reference Anything

Bring anything into context of AI and build content in seconds

YouTube

PDF

DOCX

TikTok

Web

Reels

Video Files

Twitter Videos

Facebook/Meta Ads

Tweets

Coming Soon

Audio Files

Coming Soon

Choose a plan to match your needs

Upgrade or cancel subscriptions anytime. All prices are in USD.

Basic

For normal daily use. Ideal for getting into AI automation and ideation.

$30/month
  • See what Basic gets you
  • 11,000 credits per month
  • Access to all AI models
  • 5 app schedules
  • Free optional onboarding call
  • 1,000 extra credits for $6
Get Started

No risk, cancel anytime.

ProRecommended

For power users with high-volume needs.

$100/month
  • See what Pro gets you
  • 33,000 credits per month
  • Access to all AI models
  • 10 app schedules
  • Remove AI Flow Chat branding from embedded apps
  • Free optional onboarding call
  • 2,000 extra credits for $6
Get Started

No risk, cancel anytime.

Frequently Asked Questions

Everything you need to know about AI Flow Chat. Still have questions? Contact us.