πŸ˜ƒ Basics
🧠 Advanced
Zero-Shot
🟒 Introduction
🟒 Emotion Prompting
🟒 Role Prompting
🟒 Re-reading (RE2)
🟒 Rephrase and Respond (RaR)
🟦 SimToM
β—† System 2 Attention (S2A)
Few-Shot
🟒 Introduction
🟒 Self-Ask
🟒 Self Generated In-Context Learning (SG-ICL)
🟒 Chain-of-Dictionary (CoD)
🟒 Cue-CoT
🟦 Chain of Knowledge (CoK)
β—† K-Nearest Neighbor (KNN)
β—†β—† Vote-K
β—†β—† Prompt Mining
Thought Generation
🟒 Introduction
🟒 Chain of Draft (CoD)
🟦 Contrastive Chain-of-Thought
🟦 Automatic Chain of Thought (Auto-CoT)
🟦 Tabular Chain-of-Thought (Tab-CoT)
🟦 Memory-of-Thought (MoT)
🟦 Active Prompting
🟦 Analogical Prompting
🟦 Complexity-Based Prompting
🟦 Step-Back Prompting
🟦 Thread of Thought (ThoT)
Ensembling
🟒 Introduction
🟒 Universal Self-Consistency
🟦 Mixture of Reasoning Experts (MoRE)
🟦 Max Mutual Information (MMI) Method
🟦 Prompt Paraphrasing
🟦 DiVeRSe (Diverse Verifier on Reasoning Step)
🟦 Universal Self-Adaptive Prompting (USP)
🟦 Consistency-based Self-adaptive Prompting (COSP)
🟦 Multi-Chain Reasoning (MCR)
Self-Criticism
🟒 Introduction
🟒 Self-Calibration
🟒 Chain of Density (CoD)
🟒 Chain-of-Verification (CoVe)
🟦 Self-Refine
🟦 Cumulative Reasoning
🟦 Reversing Chain-of-Thought (RCoT)
β—† Self-Verification
Decomposition
🟒 Introduction
🟒 Chain-of-Logic
🟦 Decomposed Prompting
🟦 Plan-and-Solve Prompting
🟦 Program of Thoughts
🟦 Tree of Thoughts
🟦 Chain of Code (CoC)
🟦 Duty-Distinct Chain-of-Thought (DDCoT)
β—† Faithful Chain-of-Thought
β—† Recursion of Thought
β—† Skeleton-of-Thought
πŸ”“ Prompt Hacking
🟒 Defensive Measures
🟒 Introduction
🟒 Filtering
🟒 Instruction Defense
🟒 Post-Prompting
🟒 Random Sequence Enclosure
🟒 Sandwich Defense
🟒 XML Tagging
🟒 Separate LLM Evaluation
🟒 Other Approaches
🟒 Offensive Measures
🟒 Introduction
🟒 Simple Instruction Attack
🟒 Context Ignoring Attack
🟒 Compound Instruction Attack
🟒 Special Case Attack
🟒 Few-Shot Attack
🟒 Refusal Suppression
🟒 Context Switching Attack
🟒 Obfuscation/Token Smuggling
🟒 Task Deflection Attack
🟒 Payload Splitting
🟒 Defined Dictionary Attack
🟒 Indirect Injection
🟒 Recursive Injection
🟒 Code Injection
🟒 Virtualization
🟒 Pretending
🟒 Alignment Hacking
🟒 Authorized User
🟒 DAN (Do Anything Now)
🟒 Bad Chain
πŸ”¨ Tooling
Prompt Engineering IDEs
🟒 Introduction
GPT-3 Playground
Dust
Soaked
Everyprompt
Prompt IDE
PromptTools
PromptSource
PromptChainer
Prompts.ai
Snorkel 🚧
Human Loop
Spellbook 🚧
Kolla Prompt 🚧
Lang Chain
OpenPrompt
OpenAI DALLE IDE
Dream Studio
Patience
Promptmetheus
PromptSandbox.io
The Forge AI
AnySolve
Conclusion

ChatGPT Basics

🟒 This article is rated easy
Reading Time: 7 minutes
Last updated on March 6th, 2025

Valeriia Kuka

Throughout this Basics Guide, we'll be using ChatGPT, one of the most popular and accessible AI chatbots. ChatGPT is known for its versatility and ease of use, supporting a wide range of tasks from simple queries to complex problem-solving.

ChatGPT's user interface features a clean, conversation-style layout where you can type prompts and receive AI-generated responses.


While there are other AI tools available, we've chosen ChatGPT for its broad capabilities and user-friendly setup, making it a great starting point for learning and experimenting with AI models.

Tip
For a more detailed introduction to ChatGPT with visual step-by-step guidance, check out our free course, ChatGPT for Everyone.

In this section, we'll walk you through setting up ChatGPT and demonstrate its uses for a variety of tasks, from simple queries to more advanced applications like summarizing articles and solving math problems.

Set up ChatGPT

Getting started with ChatGPT is simple:

  • Navigate to http://chat.openai.com
  • It should ask you to make an account. Go ahead and do so.
  • Log in with this account

Need help with setup? Here's a helpful video to guide you through:

Mobile Setup

You can also download the ChatGPT app from your device's app store (iOS/Android). The interface is similar, and you can log in with the same account.

Try Out Some Prompts with ChatGPT

Now that you've set up ChatGPT, let's try out a few prompts for simple and more advanced tasks.

Note

A prompt is the input or instruction given to an AI model to generate a response. Prompts can be simple (a question) or complex (detailed instructions with context, tone, style, and format specifications). The quality of the AI's response depends directly on how clear, detailed, and structured the prompt is. You can read more about prompts in our article about prompt engineering.

Keep in mind that prompt can be a verb or a noun. You can prompt a model, or you can give a model a prompt. Both mean the same thing, and the process of interacting with the model this way is called prompting. We'll dive deeper into prompt engineering techniques in next lessons.

Simple Query: Color of Grass

Let's start with a very simple question. Can ChatGPT tell us the color of grass?

Astronaut

Prompt


What color is grass?

Robot

AI Output


Grass is green.

This is a straightforward factual query. It's a great way to get a feel for how ChatGPT responds to simple inputs.

Summarizing an Article

Now, let's try something more practical: summarizing a paragraph. Say you're reading an article about snowfall in Florida and want to quickly grasp the main points.

You can paste the paragraph into ChatGPT and ask for a summary :

Astronaut

Prompt


It is very rare for snow to fall in the U.S. state of Florida, especially in the central and southern portions of the state. Except for the far northern areas of the state, most of the major cities in Florida have never recorded measurable snowfall, though trace amounts have been recorded, or flurries in the air observed a few times each century. According to the National Weather Service, in the Florida Keys and Key West, there is no known occurrence of snow flurries since the European colonization of the region more than 300 years ago. In Miami, Fort Lauderdale, and Palm Beach there has been only one known report of snow flurries observed in the air in more than 200 years; this occurred in January 1977. In any event, Miami, Fort Lauderdale, and Palm Beach have not seen snow flurries before or since this 1977 event.

Summarize this paragraph in a single sentence:

Here's the response:

Robot

AI Output


Snowfall is extremely rare in Florida, except for the far northern areas, and only one instance of snow flurries in the air has been recorded in the major cities of Miami, Fort Lauderdale, and Palm Beach in the last 200 years.

Caution

Your result may differ slightly because ChatGPT's responses can vary. We'll explain why later in this guide.

Solving Math Problems

ChatGPT can also solve math problems! Let's give it a simple arithmetic problem to see how it handles math.

Astronaut

Prompt


If I have 20 apples, eat three of them, and sell three more, how many do I have left?

Robot

AI Output


If you have 20 apples and you eat three of them, you will have 20 - 3 = 17 apples left.

After eating three apples (17 left), if you sell three more, you will have 17 - 3 = 14 apples left.

It's that simple! ChatGPT can handle both basic and more advanced math problems, even walking you through solutions step-by-step for more complicated calculations.

Best Practices for Prompting ChatGPT

Here are some helpful tips for writing prompts to get better results from ChatGPT:

  1. Be specific and clear: Provide detailed context and use actionable verbs in your prompts.

Instead of vague prompts like "Tell me about grass", try:

Astronaut

Prompt


Analyze the characteristics of grass in temperate regions, focusing on:

  1. Typical color variations by season
  2. Average height
  3. Common species Format the response as bullet points.

Tips for clear prompts:

  • Use clear action verbs (analyze, explain, summarize, list)
  • Specify the desired format
  • Include relevant context
  • Define any constraints
  1. Structure your prompts: Use clear formatting and organization.
Astronaut

Prompt


Context: Analyzing a scientific research paper

Task: Create a summary

Constraints: Maximum 100 words

Format: Use the following structure:

  • Main finding
  • Key methodology
  • Implications

Tips for structuring prompts:

  • Use prefixes to label different parts (Input:, Context:, Task:, Format:)
  • Break complex requirements into numbered lists
  • Specify output format explicitly
  1. Include necessary context: Provide background information and specify how it should be used.
Astronaut

Prompt


Context: I'm a high school teacher preparing a lesson on photosynthesis

Audience: 10th-grade students

Task: Create an explanation of photosynthesis that:

  • Uses simple analogies
  • Includes 3 key concepts
  • Avoids technical jargon

Length: 2-3 paragraphs

  1. Use few-shot examples: When needed, provide examples to guide the output format.
Astronaut

Prompt


Convert these dates to ISO format. Follow these examples:

Input: March 15, 2024

Output: 2024-03-15

Input: December 31, 2023

Output: 2023-12-31

Now convert: January 1, 2025

  1. Iterate and refine: Don't hesitate to refine your prompts based on responses.
  • Start with clear, specific instructions
  • Use structured formatting with prefixes
  • Include relevant context and constraints
  • Provide examples when format is important
  • Iterate and refine based on responses
  • Break complex tasks into smaller steps
Note

While we've covered some key tips here like providing context and using examples, you can find many more detailed recommendations for writing effective prompts in our Tips for Writing Better Prompts section. Feel free to check it out!

Conclusion

You should now be comfortable with what a prompt is and how to do some basic prompting with ChatGPT. Remember that prompts are the core of how you interact with AI models like ChatGPT, and effective prompting can lead to more accurate and useful responses.

Solving Common Issues

Quick Recap

Footnotes

  1. This paragraph is from https://en.wikipedia.org/wiki/Snow_in_Florida ↩

Valeriia Kuka

Valeriia Kuka, Head of Content at Learn Prompting, is passionate about making AI and ML accessible. Valeriia previously grew a 60K+ follower AI-focused social media account, earning reposts from Stanford NLP, Amazon Research, Hugging Face, and AI researchers. She has also worked with AI/ML newsletters and global communities with 100K+ members and authored clear and concise explainers and historical articles.