We spent about $80 purchasing five premium ChatGPT prompts and conducted a blind test among members of our marketing team to see if they were worth it.
To put it briefly: they are not.
The experiment
Here’s what I did:
- I signed up for a service that sells ChatGPT prompts and selected five SEO prompts
- I created simple versions of these prompts (27 words on average, versus 227 for the premium prompts).
- I entered these prompts into ChatGPT
- I took the edition and ran a blind poll asking Ahrefs’ marketing team to guess which edition was better.
A total of 15 people took part in the survey.
Here are the results:
The premium prompts only convincingly “beat” the basic prompt on two tasks.
Considering that you have to spend money (in some cases a lot) on these pre-built prompts, I’m skeptical that they’re even worth it. I don’t think you’re missing out on anything if you don’t pay.
The anatomy of a “premium” prompt
Almost all of the “constructed” prompts we tested had a similar structure.
I tried to break down what I saw:
In detail, here are the patterns:
- role – Requires ChatGPT to act as a professional or expert with specific skills.
- Target language – Prompts ChatGPT to respond in a specific language.
- Ultra-specific instructions – Requests ChatGPT to perform XYZ action in extreme detail.
- The focus is on human-like writing – Prompts ChatGPT to write in a specific tone or style.
- Specific edition – Requests ChatGPT to structure its response in a specific format, e.g. B. Markdown, tables, code fields, etc.
Taking that away
This experiment is in no way academic or scientific. It’s just a fun, informal test to see if “constructed” prompts perform better than a simple command.at least according to human interpretation.
However, based on the results, I’m not convinced that “Premium” encourages this Really Do so much for yourself. It’s probably better to start simple and then refine accordingly.
So don’t waste your money. Use it to upgrade to ChatGPT Plus instead.
What do you think? let me know Twitter X.
