How to Write Prompts for ChatGPT

Indeed, prompting is both the easy part and the most difficult part of using a generative artificial intelligence (AI) model, like ChatGPT. Difficulties in the complexity of cues and nuances in text-based prompts are why some organizations have a prompt engineering job role.

What is a ChatGPT prompt? It's a phrase or sentence that you write in ChatGPT to initiate a response from the AI. ChatGPT responds based on its existing knowledge base.

Don't have time to read the entire article? Jump to the quick read summary.

Prompt engineering is the act of crafting an input, which is a deed borne partly of art and partly of logic. And yes, you can do this! However, you might want to practice and polish your prompting skills before you apply for a job.

Considering how to prompt ChatGPT, if you have a good command of the subtleties of language and great critical-thinking and problem-solving skills, seasoned with more than a dash of intuitive intelligence, you’ll be amazed at the responses you can tease out of this technology with a single, well-worded prompt.

When you prompt ChatGPT, you are embedding the task description in the input (called the prompt) in a natural-language format, rather than entering explicit instructions via computer code.

Prompt engineers can be trained AI professionals or people who possess sufficient intuitive intelligence or skills transferrable to crafting the best prompts for ChatGPT (or other generative AI platforms) that solicit the desired outputs. One example of a transferrable skill is a journalist’s ability to tease out the answers they seek in an interview by using direct or indirect methods.

Prompt-based learning is a strategy AI engineers use to train large language models. The engineers make the model multipurpose to avoid retraining it for each new language-based task.

Currently, the demand for talented writers who know how to write a prompt, or prompt engineers, is very high. However, there is a strong debate as to whether employers should delineate this unique skill as a dedicated job role, a new profession, or a universal skill to be required of most workers, much like typing skills are today.

Meanwhile, people are sharing their prompts with other ChatGPT users in several forums. You can see one example on GitHub.

How to write a prompt

If you enter a basic prompt, you’ll get a bare-bones, encyclopedic-like answer, as shown in the figure below. Do that enough times and you’ll convince yourself that this is just a toy and you can get better results from an internet search engine. This is a typical novice’s mistake and a primary reason why beginners give up before they fully grasp what ChatGPT is and can do.

Understand that your previous experience with keywords and search engines does not apply here. To write awesome ChatGPT prompts, you must think of and use ChatGPT in a different way. Think hard about how you’re going to word your prompt. You have many options to consider. You can assign ChatGPT a role or a persona, or several personas and roles if you decide it should respond as a team, as illustrated in the following figure.

You can assign yourself a new role or persona as well. Or tell it to address any type of audience, such as a high school graduating class, a surgical team, or attendees at a concert or a technology conference.

You can set the stage or situation in great or minimum detail. You can ask a question, give it a command, or require specific behaviors.

A prompt, as you can see now, is much more than a question or a command. Your success with ChatGPT hinges on your ability to master crafting a prompt in such a way as to trigger the precise response you seek.

Ask yourself these questions as you are writing or evaluating your prompt:

• Who do you want ChatGPT to be?
• Where, when, and what is the situation or circumstances you want ChatGPT’s response framed within?
• Is the question you're entering in the prompt the real question you want it to answer, or were you trying to ask something else?
• Is the command you're prompting complete enough for ChatGPT to draw from sufficient context to give you a fuller, more complete, and richly nuanced response?
• And the ultimate question for you to consider: Is your prompt specific and detailed, or vague and meandering? Whichever is the case, that’s what ChatGPT will mirror in its response.

ChatGPT’s responses are only as good as your prompt. That’s because the prompt starts a pattern that ChatGPT must then complete. Be intentional and concise about how you present that pattern starter — the prompt.

For more details on using ChatGPT, including how to start a chat, reviewing your chat history, and much more, check out my book ChatGPT For Dummies.

Thinking in threads

Conversations happen when one entity’s expression initiates and influences another entity’s response. Most conversations do not conclude after a simple one-two exchange like this, but rather continue in a flow of responses cued by the interaction with the other participant. The resulting string of messages in a conversation is called a thread.

To increase your success with ChatGPT, write prompts as part of a thread rather than as standalone queries. In this way, you'll craft prompts targeted towards the outputs you seek, building one output on another to reach a predetermined end. In other words, you don’t have to pile everything into one prompt. You can write a series of prompts to more precisely direct ChatGPT’s “thought processes.”

Basic prompts result in responses that can be too general or vague. When you think in threads, you’re not aiming to craft a series of basic prompts; you’re looking to break down what you seek into prompt blocks that aim ChatGPT’s responses in the direction you want the conversation to go. In effect, you're using serialized prompts to manipulate the content and direction of ChatGPT's response.

Does it work all the time? No, of course not. ChatGPT can opt for an entirely different response than expected, repeat an earlier response, or simply hallucinate one. But serialized prompts do work often enough to enable you to keep the conversation targeted and the responses flowing toward the end you seek.

You can use this method to shape a single prompt by imagining someone asking for clarification of your thought or question. Write the prompt so that it includes that information, and the AI model will have more of the context it needs to deliver an intelligent and refined answer.

ChatGPT will not ask for clarification of your prompt; it will guess at your meaning instead. You’ll typically get better quality responses by clarifying your meaning in the prompt itself at the outset.

Chaining prompts and other tips and strategies

Here’s a handy list of other tips and refinements to help get you started on the path to mastering the art of the prompt:

• Plan to spend more time than expected on crafting a prompt. No matter how many times you write prompts, the next one you write won’t be any easier to do. Don’t rush this part.
• Start by defining the goal. What exactly do you want ChatGPT to deliver? Craft your prompt to push ChatGPT towards that goal; if you know where you want to end up, you’ll be able to craft a prompt that will get you there.
• Think like a storyteller, not an inquisitor. Give ChatGPT a character or a knowledge level from which it should shape its answer. For example, tell ChatGPT that it's a chemist, an oncologist, a consultant, or any other job role. You can also instruct it to answer as if it were a famous person, such as Churchill, Shakespeare, or Einstein, or a fictional character such as Rocky. Give it a sample of your own writing and instruct ChatGPT to write its answer to your question, or complete the task in the way you would.
• Remember that any task or thinking exercise (within reason and the law) is fair game and within ChatGPT’s general scope. For example, instruct ChatGPT to check your homework, your kids’ homework, or its own homework. Enter something such as computer code or a text passage in quotation marks and instruct ChatGPT to find errors in it or in the logic behind it. Or skip the homework checking and ask it to help you think instead. Ask it to finish a thought, an exercise, or a mathematical equation that has you stumped. The only limit to what you can ask is your own imagination and whatever few safety rules the AI trainer installed.
• Be specific. The more details you include in the prompt, the better. Basic prompts lead to basic responses. More specific and concise prompts lead to more detailed responses, more nuanced responses, and better performance in ChatGPT’s responses — and usually well within token limits.

• Use prompt chains as a way of strategizing. Prompt chaining is a technique used to build chatbots, but we can reimagine it here as a way to develop a strategic plan using combined or serial prompting in ChatGPT. This technique uses multiple prompts to guide ChatGPT through a more complex thought process.

  You can use multiple prompts as a single input, such as telling ChatGPT it's a team consisting of several members with different roles, all of whom are to answer the one prompt you entered. Or you can use multiple prompts in a sequence in which the output of one becomes the input of the next. In this case, each response builds on the prompt you just entered and the prompts you entered earlier. This type of a prompt chain forms organically, unless you stop ChatGPT from considering earlier prompts in its responses by starting a new chat.

• Use prompt libraries and tools to improve your prompting. Some examples follows:
• Check out the Awesome ChatGPT Prompts repository on GitHub at https://github.com/f/awesome-chatgpt-prompts
• Use a prompt generator to ask ChatGPT to improve your prompt by visiting PromptGenerator.
• Visit ChatGPT and Bing AI Prompts on GitHub.
• Use a tool such as Hugging Face’s ChatGPT Prompt Generator.
• Try specialized prompt templates, such as the curated list for sales and marketing use cases at Tooltester.

On GitHub, you can find tons of curated lists in repositories as well as lots of free prompting tools from a variety of sources. Just make sure that you double-check sources, apps, and browser extensions for malware before using or relying on them.