The Five Principles of Prompting are as follows:
- Give Direction: Describe the desired style in detail, or reference a relevant persona
- Specify Format: Define what rules to follow, and the required structure of the response
- Provide Examples: Insert a diverse set of test cases where the task was done correctly
- Evaluate Quality: Identify errors and rate responses, testing what drives performance.
- Divide Labor: Split tasks into multiple steps, chained together for complex goals
Give Direction
Direction is one of the most commonly used and broadest principles. It can take the form of simply using the right descriptive words to clarify your intent, or channeling the personas of relevant business celebrities. While too much direction can narrow the creativity of the model, too little direction is the more common problem.
Role Playing
A human would struggle to complete task without a good brief (detailed briefing on any task). On the similar lines, go generate a good output from AI, provide it with appropriate direction. In the below example prompt we gave direction through the use of role-playing, in that case emulating the style of Elon Musk.
Brainstorm a list of product names for a shoe that fits any foot size, in the style of Elon Musk.
Return the results as a comma-separated list, in this format:
Product description: A shoe that fits any foot size
Product names: [list of 3 product names]
## Examples
Product description: A refrigerator that dispenses beer
Product names: Teslacool, FridgeX, Neuradrink
Product description: A watch that can tell accurate time in space
Product names: WatchX, iSpace, The Watch CompanyPrewarming
There are also some rules or best practices you would do well to follow, which could be included in the prompt as context to guide the AI toward a name that works. This technique is sometimes referred to as prewarming or internal retrieval. Starting the conversation asking for best practice advice, then asking it to follow its own advice, can help a lot. In effect, you are using it to generate its own direction.
Input:
Please give me 5 tips for naming products based on expert industry advice.
Output:
Certainly! Naming a product is crucial as it often gives the first impression to potential customers. Here are five expert tips to guide you in naming products:
1. **Simplicity & Memorability**: Opt for names that are short, easy to spell, and memorable. Long, complicated names can be difficult for customers to recall.
...
5. **Positive Connotations**: Names that evoke positive emotions or imagery can create a favorable perception of your product. Then within the same chat window, where the model has the context of the past advice it gave, you ask your initial prompt for the task you wanted to complete.
Input:
Using this advice, can I have a list of product names for a pair of shoes that can fit any foot size?
Output:
Certainly! Based on the criteria given, here's a list of potential product names for shoes that can fit any foot size:
1. **FitAll Walkers**: A simple and memorable name that
instantly suggests a universal fit.
...
10. **TrueFit Universals**: Emphasizing genuine comfort and
fit for all.Context
Another fruitful strategy in our experience is to take the best advice out there for the task you want to accomplish and insert that context into the prompt. In the below example, context is given after each criteria.
Input
Can I have a list of product names for a pair of shoes that can fit any foot size? Please follow the five rules below:
1. It should be readable and writable.
If your product name is hard to pronounce, people won’t talk about it, and if they can’t write it down (and spell it correctly!) when they hear it, how do you expect them to Google it?
Keep it simple and don’t go with any wacky spellings just for the sake of it.
...
5. It should evoke an emotion, feeling, or idea.
Your product name should tie back into what your product is, what the feeling you want people to have when experiencing your product is, and/or what idea are you trying to get across.
It should be emotive and inspiring.Specify Format
AI models are universal translators. These models are capable of returning a response in almost any format, so an important part of prompt engineering is finding ways to specify what format you want the response to be in. Just like when working with a human, you can avoid wasted effort by specifying up front the format you expect the response to be in.
Input:
Return a comma-separated list of product names in JSON for "A pair of shoes that can fit any foot size.". Return only JSON.
Examples:
[{
"Product description": "A home milkshake maker.",
"Product names": ["HomeShaker", "Fit Shaker",
"QuickShake", "Shake Maker"]
},
{
"Product description": "A watch that can tell
accurate time in space.",
"Product names": ["AstroTime", "SpaceGuard",
"Orbit-Accurate", "EliptoTime"]}
]
Output:
[
{
"Product description": "A pair of shoes that can \
fit any foot size.",
"Product names": ["FlexFit Footwear", "OneSize Step",
"Adapt-a-Shoe", "Universal Walker"]
}
]Provide Examples
If you’re providing zero examples, you’re asking for a lot without giving much in return. Even providing one example (one-shot) helps considerably, and it’s the norm among researchers to test how models perform with multiple examples (few-shot). Adding one example along with a prompt can improve accuracy in some tasks from 10% to near 50%!
There’s a trade-off between reliability and creativity: go past three to five examples and your results will become more reliable, while sacrificing creativity. The more examples you provide, and the lesser the diversity between them, the more constrained the response will be to match your examples.