You might think that ChatGPT would be the best resource to learn about how to design a good AI LLM prompt, however humans are definitely better right now.

Prompt Need - Business Idea Market Analysis

I'm working to build automated market analysis for business ideas into the CompanyCraft product. I tried using ChatGPT-4 to get help on one of the prompts I'm using. This blog shows you the results of that experiment

This is the business idea I'm testing with (by the way, if anyone wants to make this product, let me know, I'll be your first customer!):

• Name: Smart Grass Product for Weed Suppression
• Summary: A low-maintenance grass product that suppresses weeds and requires minimal watering, ideal for landscaping and forestry businesses.

Human Prompt Engineering

I queried OpenAI's GPT-4 chat API endpoint to have it generate 3 best-fit market names for that business idea. With the prompt I made, it returned these results:

• "Landscaping Products"
• "Turf and Ornamental Products"
• "Weed Control Products"

Not bad! But I was getting a bit too much variation on the results at times, so I figured I would ask ChatGPT to improve the prompt.

ChatGPT-4 Prompt Engineering

I copied and pasted the prompt I had made and asked it if I should make any changes

‍

After making the changes it suggested, I got these results:

• "Landscaping Services"
• "Forestry Services"
• "Turf and Lawn Care Supplies"

Almost useless.

Conclusion

The 2 prompts aren't dramatically different. Mine uses a bulleted list of criteria that the market name should meet. ChatGPT's morphs that list into a single line of text (3 sentences).

So, lessons learned, bullet points are good, even if ChatGPT doesn't think so. And humans are still smarter than AI at prompt engineering.