To use ChatGPT or not to use ChatGPT? Is that really the question anymore?
If you're like me, you already use this tool to amplify your awesomeness. Like improving your email writing, analyzing data faster, or firing up your social media strategy.
But I have to admit 鈥� it鈥檚 not all peaches and cream. And others seem to agree 鈥� marketers we surveyed stated ChatGPT outputs aren鈥檛 publishable .
Does this mean you should throw the whole AI concept away? Not at all. Your outputs are only as good as your prompting skills.
So, I spoke to 探花精选's SEO team to understand how to write prompts for ChatGPT. Stick around to see the key elements of a good prompt, helpful ChatGPT prompt tips, and prompt writing examples.
Table of Contents
It's tempting to load up ChatGPT and jump right into the prompt. However, , Associate SEO Strategist at 探花精选, recommends a more introspective approach.
鈥淭he first thing you should do is figure out what you want. Before I type anything, I always take a moment to envision what the final output will look like,鈥� he told me.
He gives an example of a marketer who wants to generate a marketing plan.
Instead of typing 鈥淲rite me a marketing plan鈥� into ChatGPT, she should take the time to envision what the plan looks like 鈥� how many sections it has, how many bullet points are under each section, and what information it contains.
Now that she has a better grasp of the task at hand, it becomes much easier to compose a prompt that checks all the boxes.
AI models thrive on specificity. If you feed it with vague instructions, you give it room to interpret what it thinks you want.
For example, suppose you prompt ChatGPT to 鈥淩ewrite this [article/email/Tweet],鈥� expecting it to write something new and original. Instead, it regurgitates your original message using the same words and phrases.
The solution is to get specific and intentional with your words.
Instead of 鈥淩ewrite,鈥� for instance, you might say reimagine, expand, simplify, or modernize. Even a small change in the way you phrase a prompt can significantly change the response.
As Blyskal points out, 鈥淎 lot of people treat AI like a rigid system that can be hacked with the right words or phrases, but that's not the case.
There are no secret keywords that can guarantee the best results. It's like playing a game of words, and you have to think intentionally about the ones you use.鈥�
You could get away with stopping at the previous step 鈥� especially if your request is fairly straightforward (e.g., 鈥淲rite five knock-knock jokes for kids鈥�).
However, you can supercharge your prompts by padding them with context. This gives the AI model more ingredients to cook up a great response.
, former SEO Specialist at 探花精选, puts it this way:
鈥淪uppose your friend asks you to go to the store and pick up a few things. You definitely need more context 鈥� which store, what things, what's the budget, and so on. The more context you get from your friend, the easier it is to do the task. The same goes for AI!鈥�
Let's look at an example:
Both of these prompts might yield good results, but the second prompt will give you a more detailed and compelling description.
This is because the AI model has more context to work with, including the product's name (鈥淪queaky Queen鈥�), its form (a scrub), and its key features (vegan, gluten-free, recyclable packaging).
Although AI models are powerful, they still need you to take the lead. Without clear instructions, they're essentially a chef without a recipe or a new employee without a handbook.
Here's an example: Imagine you need to write an article about Instagram marketing. Along with the main task ("Write an article about Instagram marketing"), you also instruct ChatGPT to:
Not only are you giving ChatGPT a clear topic, but you鈥榬e also guiding and shaping the content itself. You鈥檙e adding quotes, statistics, and examples to give the output more texture.
Of course, it's not just what you say but how you say it. The content of the article might be up to par, but it may lack a unique voice or perspective. This is where style and tones come in.
For , 探花精选 Senior Technical SEO Specialist, adding style to prompts is a multi-step process. He starts by letting the AI tool generate a general answer and then progressively molds its response for style.
鈥淵ou can ask it to inspire itself from a situation, character, or profession, or provide it with already made examples to emulate,鈥� he told me.
Charbit also incorporates ChatGPT tone modifiers, such as 鈥渃heerful,鈥� 鈥渉umorous,鈥� or 鈥渁uthoritative,鈥� to guide the AI further.
Let's look at some examples:
Other style parameters include length and format. You can specify the length of the response (e.g., 鈥淜eep the article under 800 characters鈥�) and its format (e.g., 鈥淐reate a list of bullet points鈥�).
Blyskal follows the 60% Rule.
He told me, 鈥淲hen you generate something and it's at least 60% of what you want, you should continue refining that specific prompt. But if it falls short of that, it might be time to start from scratch.鈥�
So, if you ask ChatGPT to generate a list of ten blog ideas and you only like two, it's a good indication to go back to the drawing board.
Even if you meet the 60% threshold, you can still refine the output by giving follow-up instructions such as, 鈥淢ake it sound more conversational鈥� or 鈥淐ondense this into one paragraph.鈥�
Remember that prompt writing isn't an exact science. Like any creative process, it often takes multiple revisions to get the right output.
Role-playing is a technique that involves asking the AI model to adopt a specific role, job, or function.
鈥淲hen you ask an AI model to play a specific role, you're giving it a certain level of expertise,鈥� Blyskal told me. 鈥淔or instance, if you prompt it to act as a professional interviewer, it will look for examples of good interviewing skills and respond with professional-seeming questions.鈥�
By defining a role for the AI model to play 鈥� such as a professional interviewer, a graphic designer, or a nutritionist 鈥� you're also tapping into different viewpoints and perspectives, which can be especially helpful for marketers.
For example, let鈥榮 say you鈥檙e launching a new product, a cold plunge tub. You need to create an ad that appeals to your target audience: long-distance runners. In this scenario, you ask the AI model to play the role of a long-distance runner and list the key benefits of your product.
Here鈥檚 an example from Perplexity (my fave AI tool) because it provides images and links to sources (peace out hallucinations):
Now, the AI model will generate responses that align with the needs and preferences of long-distance runners. This gives you valuable insight into your audience, enabling you to create a more compelling and relevant ad.
Imagine you鈥榬e on a road trip, and you鈥檙e relying on GPS to guide you from point A to point B. Throughout the journey, it gives you turn-by-turn directions until you reach your destination.
Chain of thought prompting follows a similar approach. You give the AI model one prompt after another, with each prompt building on the one before it. This keeps the model on track, giving you greater control of the output.
鈥淵ou're basically asking the AI model to explain its reasoning at each step. If you don't like any of the explanations, you can tinker with the output until it's ready for the next prompt,鈥� Blyskal explains.
This is ideal for tasks that can be broken down into smaller steps.
For example, consider a copywriter using AI to create an article. She first prompts it to create an outline. Once she鈥榮 happy with the outline, she prompts it to write the article, and then the headline, and then the meta description. She doesn鈥檛 move to the next step until she's satisfied with the current output.
That's the power of chain prompting. By guiding the model in a logical sequence, you generate more accurate and relevant responses.
鈥淚f there's any one tip that will take your prompting to the next level, it's providing examples to the AI model,鈥� Blyskal told me.
You can think of examples as reference points, helping the AI model emulate a certain style, tone, structure, or format. On top of that, AI can analyze a piece of content and offer improvements.
Here are several types of examples you can provide to ChatGPT:
While AI prompting is a science, it鈥檚 also an art. So don鈥檛 be afraid to get creative with your examples and instructions to get out-of-the-box outputs.
Here are three use cases I鈥檓 seeing many people use in content marketing today. I included the prompt, why it works, and the generated output by ChatGPT.
Prompt: 鈥淐reate a social media campaign to launch our new eco-friendly water bottle. The campaign should include 5 Instagram posts, 3 Facebook posts, and 2 X posts. Each post should highlight the product's sustainability features, target eco-conscious consumers, and include a call-to-action to visit our website.鈥�
Why it works:
Generation:
Fun fact: 31% of marketers use AI for social media post creation based on our .
Prompt: 鈥淒raft an email marketing campaign for our upcoming summer sale. The email should be engaging, highlight the 20% discount on all summer clothing, and include a clear call-to-action to shop now. Target young adults aged 18-30.鈥�
Why it works:
Generation:
Fun fact: We found 28% of marketers use ChatGPT to create and answer emails.
Prompt: 鈥淐reate a PPC ad campaign for our digital marketing consultancy. The campaign should include 3 Google Ads and 2 Facebook Ads. Highlight our expertise in SEO and social media marketing, and include a call-to-action to book a free consultation.鈥�
Why it works:
Generation:
Fun fact: 90% of marketers see AI reducing time spent on manual tasks (like creating ads).
Blyskal said it best: 鈥淎t the core of prompting is conversation.鈥� You don't engineer or program AI. Instead, you talk to it.
Like any conversation, you naturally adjust your tone, provide ample context, and share details, anecdotes, and examples to give your story texture. These are the same elements that make a really great prompt.
Editor's note: This post was originally published in July 2023 and has been updated for comprehensiveness.