Because you are likely excited to start using ChatGPT though in your own work (and you should!) I want to give you a basic rundown of how to create great prompts.
Let’s start basic.
Prompts at their core are just text containing instructions for the AI.
However, how you structure that text matters. Here are some prompt best practices:
Use clear, straightforward language - Avoid ambiguity
Keep sentences simple and declarative
Add line breaks between logical sections
Number steps if giving multi-step instructions
Use consistent formatting and punctuation
Capitalize names and titles properly to avoid confusion
Adhering to basic conventions will make your prompts clearer and easier for the AI to understand.
If in doubt just make your writing clear. Imagine you were writing to a human. What instructions would you need to make sure they absolutely “get it” first time?
A fun thought experiment here is to imagine you are renting our your house as an AirBnb.
We need to write very detailed instructions to the guest so they can find the key, get in, turn off the alarm, turn on the boiler, work out how to use the TV etc. etc.
You will not be there for them. You’ll be (hopefully) on beach somewhere away from your phone.
Therefore nailing the instructions so that there is zero ambiguity and any guest can easily follow them is key.
Think like this with ChatGPT and you’ll be golden.
Effective prompts generally contain some combination of the following components:
Context not assuming knowledge
Relevant background info to inform the AI
Defines terminology, personalities, goals, etc.
Don’t assume the AI knows what you want. Instead treat them like Chad - someone who is intelligent but doesn’t know how things work yet. You have to provide context around your prompt to give all the information required to complete the task.
Instructions not Questions
Clear directions telling the AI what to generate/do
Often written imperatively (e.g. "Write a poem...")
Can include multi-step numbered directions
Don’t use questions with AI in the same way you might on Google. Asking questions leads to more wishy-washy answers. Instead instructions work far better.
Examples
Illustrative samples guiding the desired output
Provide 1-2 examples minimum
Don’t be annoyed when the AI provides an output that doesn’t match what you are expecting. You need to show the AI what a good output looks like so that it can best match your expectations.
Constraints
Boundaries to restrict undesired responses
"Do not include..."
Telling an AI what to exclude is just as, if not more, important as telling it what you want. AIs can generate pretty much anything so being precise about what you don’t want in an output helps them to focus.
There’s a lot to remember here so I’ve coined a nice memory aid.
I use the RISEN method:
Role - What persona should the AI adopt?
Instructions - What clear directions are you giving?
Steps - Are there numbered steps to follow?
End goal - What is the desired output?
Narrowing - What constraints are you adding?
For example:
Act as a master chef. (Role)
Give me a 5 step recipe for baked chicken breast. (Instructions)
1. tell me the ingredients needed
2. the steps to prepare
3. cooking instructions
(steps)
Give me everything in a checklist (End goal)
Keep these constraints in mind: (Narrowing)
-Use only common ingredients
-Include approximate cooking times and temperatures
-Keep the recipe under 500 words
-Do not include any complicated techniques
-Focus just on the core recipe steps
The RISEN framework provides a structured way to build prompts that guide the AI to high-quality responses tailored to your needs.
Apply it to your tasks to immediately see improvements across the board.
Yes, your prompts will take longer to write but the results will propel you immediately from an amateur to an intermediate user.
Here’s a quick cheatsheet to help:
Use the RISEN framework and you are ahead of 90% of ChatGPT users already. Good job.
You now have more than enough basic AI knowledge to start leveraging it to build your business. Which is handy because that’s literally what we’re diving into in Module 1.
See you inside.