Philadelphia Open Innovation Tournament 2025

Prof. Ethan Mollick from Wharton recommends this powerful prompt structure for product ideation:

Generate new product ideas with the following requirements:
  The product will target college students in the United States. It should be a physical good, not a service or software. I'd like a product that could be sold at a retail price of less than about USD 50. The ideas are just ideas. The product need not yet exist, nor may it necessarily be clearly feasible.
  Follow these steps. Do each step, even if you think you do not need to:
  1.First, generate a list of 100 ideas (short title only).
  2.Second, go through the list and determine whether the ideas are different and bold. Modify the ideas as needed to make them bolder and more different. No two ideas should be the same. This is important!
  3.Next, give the ideas a name and combine it with a product description. The name and idea are separated by a colon and followed by a description. The idea should be expressed as a paragraph of 40–80 words.
  Do this step by step!

• Simply modify the target market, product type, and price point for your needs.
• This structured approach forces the AI to think broadly before refining.
• The step-by-step instructions prevent AI from skipping important ideation stages.
• Requiring uniqueness and boldness pushes past generic first-round ideas.

Recent academic research shows that AI can effectively simulate diverse customer perspectives. Try this prompt structure:

I'm developing [product name], which is [brief description].
  
  You will now act as my ideal customer persona with these characteristics:
  - Demographics: [age, gender, location, income level]
  - Goals: [what they're trying to accomplish]
  - Pain points: [current frustrations]
  - Values: [what matters most to them]
  
  As this persona, please:
  1. Evaluate my product concept honestly
  2. Tell me what you like and dislike about it
  3. Describe how you would use it in your daily life 
  4. Share how much you would pay for it and why
  5. Explain what would make you choose this over alternatives
  
  Be specific and constructive. Don't hold back criticism—I need authentic feedback.

• Create 5-7 diverse personas to identify blind spots in your concept.
• Research suggests AI-generated feedback can surface more unique issues than traditional methods.
• Use this approach to rapidly iterate before real customer testing.
• Generate likely objections from different stakeholder groups.

For an example of what can be done with almost no effort see our sample landing page and how it was made by Manus with two prompts → see the full process here.

• Generate UI mockups, product visualizations, and branding elements.
• Develop marketing copy, documentation, and user guides.
• Create code snippets or entire proof-of-concept applications.

• Ask AI to be competitor, skeptic, and regulator—patch every hole.
• Have AI evaluate your concept against potential competitors.
• Identify technical, operational, or market barriers.
• Use AI to highlight potential compliance issues.

• Problem → aha → impact. Rehearse Q&A with ChatGPT as the grumpiest investor.
• Have AI help craft a compelling story around your innovation.
• Generate professional slides and visual aids.
• Practice with AI by simulating judge questions.

• 📱 Smartphone.
• 🤖 Frontier AI: ChatGPT Plus, Claude Pro, Gemini Advanced, Mistral Le Chat Pro and/or Deepseek.
• 🛠️ Agentic AI: Manus for research and quick landing pages.

We highly recommend using the paid tiers of these tools for access to the most advanced models and features.