Thought Leaders
Mastering the Art of AI Prompts: 5 Techniques for Advanced Users
The use of large language models (LLMs) like ChatGPT is exploding across industries. Even scientists are leaning on AI to write or at least polish their work. A recent analysis of five million scientific studies published in 2023 found a rapid increase in certain words, such as meticulous, intricate, and commendable. The reason for this increase? The use of LLMs.
AI’s impact is already massive, rapidly transforming the workplace. But we’re still at the early stages, trying to strike a balance between harnessing AI without leaning too much on it and compromising quality. At my company Jotform, we have incorporated AI tools to automate tedious tasks, or as I call it, “busywork,” and free up employees to focus on the meaningful work that only humans can do. I view AI tools like ChatGPT as valuable resources—low-cost, efficient AI assistants. But as anyone who’s used ChatGPT will tell you, it’s not 100% reliable or accurate. And it’s only as effective as the prompts you give it.
I recently asked ChatGPT how to develop your prompt engineering skills. The first response was: “Experimentation and Iteration: Continuously experiment with different types of prompts and refine them based on the AI's outputs. Track what works and what doesn’t, and iteratively improve your prompts.”
In other words, practice makes perfect.
With this in mind, here are my top strategies for taking your prompt writing to the next level.
Try meta-prompts
Communication is the lynchpin of a successful relationship. Understanding how people communicate and how to best communicate with them can help grow a stronger bond and overcome inevitable misunderstandings when there is a disconnect between words and intentions or emotions. In the same vein, your interactions with ChatGPT can vastly improve if you explicitly ask it how to best communicate with it. I regularly ask ChatGPT how to phrase prompts in order to get the information or feedback I’m seeking. The more information you give ChatGPT about the results you’re after, the better it can help you generate an effective prompt.
Here’s a sample meta-prompt:
“How would you phrase a prompt to get detailed feedback on an article from ChatGPT? What information would you include to get the most relevant insight?”
In seconds, ChatGPT churned out a prompt template with a brief explanation of why it included each part of the prompt. This kind of insight helps you write better prompts in the future.
Make it an ongoing dialogue
In most research tools, each query is isolated. You can’t build on a previous search to refine or dig deeper. ChatGPT has the advantage of enabling you to continue a thread, just like a dialogue between two people—a Socratic dialogue, if you will, where you are the teacher and ChatGPT is the student. I find this capability especially useful if I’m new to a subject and would like to begin with a basic level of understanding before diving into the nitty gritty.
To engage in dialogue with ChatGPT, start with a broad prompt and refine the subsequent prompts based on the responses.
A sequence of prompts might look like this:
“In a few sentences, can you explain the mechanics of a tennis serve?”
“Why does the server shift their weight from the back foot to the front foot?”
“Can you briefly explain kinetic energy transfer?”
This technique can help you to get more nuanced responses and explore areas and perspectives you might not have otherwise considered.
Give ChatGPT a reference text
ChatGPT can be a bit of a smooth talker. Ask it about any subject under the sun and it will happily wax poetic for as long as you’d like. The rub: it’s not always accurate. That’s why providing ChatGPT a reference text can help ensure the replies you receive are grounded in reliable sources.
As OpenAI explains, “In the same way that a sheet of notes can help a student do better on a test, providing reference text to these models can help in answering with fewer fabrications.” Feed ChatGPT the sources that you already know and trust and let the LLM extract the information you need.
The prompt could be:
“Use the following article in quotes to answer questions.”
ChatGPT: Sure, please go ahead and provide the articles you'd like me to use for answering your questions.
Then, provide ChatGPT with the article (title and publication will usually do the trick) and your questions.
Assign ChatGPT a role
One of the most useful, and admittedly fun, capabilities of ChatGPT is to adopt different personas. You probably know the parable of the blind men and the elephant. Each man feels a different part of the elephant and describes the animal based on their limited perspective. As humans, we tend to assume our reality is correct even when it’s based on a limited point of view. Incorporating various perspectives empowers us to understand something more fully.
By simply instructing ChatGPT to adopt a persona, we can get a new perspective.
Consider these two prompts and personas:
Prompt: Rewrite the following text from the perspective of a poet: A bridge over water connects two lands.
ChatGPT:
Between shores, where rivers dance and whisper,
A bridge, slender and resolute, spans the liquid silver,
Uniting distant lands with an arch of promise,
A testament to the yearning of hearts and soil.
Prompt: Rewrite the following text from the perspective of an engineer: A bridge over water connects two lands.
ChatGPT
A bridge over water functions as a structural solution, effectively connecting two separate landmasses. It spans the gap with precision-engineered materials, ensuring stability and durability while facilitating transportation and communication between the two regions.
At Jotform, our marketing team might use this technique to examine an issue from the perspective of different buyer personas. It’s a simple technique with myriad use cases.
Model the reply you want
While ChatGPT might not be the most reliable narrator, it is extremely logical. Rather than trying to describe the response you want, which can be surprisingly challenging, you can give ChatGPT an example and it will apply the same logic.
Let’s say I’m working on a marketing campaign and want to use ChatGPT to come up with snappy, compelling copy.
I could use the following prompt:
Prompt: “I will write words and I'd like you to come up with a corresponding adjective. For example, if I write ‘pretty,’ you might write “more beautiful than the stars in the sky.”
ChatGPT:
Of course, I'm ready! Please provide the words you'd like me to transform.
Me: nervous
ChatGPT: Nervous as a leaf trembling in the gale of a tempest.
I might consider that on second thought, that’s not the tone I’m after. So I tweak the prompt.
Prompt: I will write words and I'd like you to come up with a corresponding adjective. For example, if I write ‘pretty,’ you might write “cuter than the prize-winning pig at the Texas State Fair.”
ChatGPT: Got it! Please provide the words you'd like me to transform.
Me: nervous
ChatGPT: Nervous as a cat at a rocking chair convention.
In this case, I’d get an idea for my marketing copy—and a chuckle, at no extra charge.