Market Demand Validation
Yesterday you built a pipeline of product ideas. Today you're going to kill most of them — and that's a good thing.
The difference between successful product developers and everyone else isn't better ideas. It's better filters. The best founders kill bad ideas fast and cheap so they can pour their time and money into the ones that actually have demand.
AI turns validation from a weeks-long, expensive process into something you can do in an afternoon. Today you'll learn the frameworks and prompts that separate ideas worth pursuing from ideas that feel good but won't sell.
The "would anyone actually buy this?" framework
Before you run any sophisticated analysis, start with the brutal question: Would a real person actually hand over money for this?
Most founders skip this question because they're in love with their idea. AI has no emotional attachment, which makes it an excellent bullshit detector.
Here's the four-part demand check:
1. Does the problem exist at scale? A problem that affects 500 people isn't a business. Ask Perplexity to estimate how many people experience the specific problem your product solves. You need thousands at minimum, ideally hundreds of thousands.
2. Are people already spending money on it? If nobody is paying for solutions — even bad ones — that's a warning sign. It means either the problem isn't painful enough or people aren't willing to pay to solve it. Both are deal-breakers.
3. Is the current solution bad enough? If excellent solutions already exist and customers are happy, there's no gap. You need the current options to be expensive, frustrating, incomplete, or outdated. Ask AI to analyse satisfaction levels with existing solutions.
4. Can you reach these people? A million people might have the problem, but if you can't find them, target them, or communicate with them affordably, the market size is irrelevant.
If your idea fails any of these four checks, move on. Don't try to force it.
Using AI to estimate market size and demand
Market sizing used to require expensive databases and analyst reports. AI can now give you a solid directional estimate in minutes — not precise enough for a venture capital pitch, but more than accurate enough to decide whether an idea is worth pursuing.
The bottom-up approach (most reliable):
Ask Perplexity to help you estimate the number of potential customers using publicly available data. For example:
"How many freelance designers are there in the UK? What percentage use project management software? What's the average spend on productivity tools per year?"
Then multiply: potential customers x likely conversion rate x price point = estimated revenue opportunity.
The top-down approach (useful for context):
Ask Perplexity: "What is the market size for [your category]? What's the growth rate?" This gives you the total market, which you then narrow down to your realistic addressable slice.
The proxy approach (when direct data doesn't exist):
If your product category is too new for market reports, look at adjacent markets. Ask AI: "What's the market size for [related product] and what percentage of those users might also need [your product]?"
No single approach gives you the full picture. Use all three and triangulate.
Analysing search trends and volume
Search data is one of the most honest signals of demand because it represents actual behaviour, not stated preferences. People search for what they genuinely want, not what they think they should want.
Google Trends analysis with AI:
Ask Perplexity to analyse Google Trends data for keywords related to your product idea. You're looking for:
- Rising trajectory — Is search interest growing month over month? A keyword with 2,000 monthly searches growing at 30% is more exciting than one with 20,000 searches that's been flat for two years.
- Seasonal patterns — Some products have seasonal demand. AI can identify whether you're looking at a permanent trend or a seasonal spike that will disappear.
- Related queries — Google Trends shows what else people search for alongside your keyword. These related queries often reveal the specific pain points driving the searches.
Search volume analysis:
Ask AI to estimate monthly search volumes for your key terms. High search volume means people are actively looking for solutions. Low search volume might mean the market is too small — or it might mean you need different keywords.
The combination signal: Rising search volume plus high complaint volume on forums plus low satisfaction with existing solutions is the strongest possible demand signal. All three together means you've found a market that's growing, frustrated, and underserved.
Testing willingness to pay
This is where most product ideas die — and where they should die if they're going to. People will happily say they want a product. Far fewer will actually pay for it. AI can help you stress-test willingness to pay before you build anything.
The substitution test. Ask AI: "What are people currently paying to solve this problem, even badly?" If they're paying nothing — not even for inferior solutions — that's a strong negative signal. If they're paying for workarounds, consultants, or cobbled-together tools, your product has a price anchor.
The "would you cancel?" test. Ask ChatGPT to role-play as your target customer and present your product at various price points. Push back on the positive responses: "Why would you pay £15/month when you could just use a spreadsheet?" A well-constructed AI role-play will surface the real objections.
The comparison test. Ask AI to find 5 products in adjacent markets that target a similar audience. What do they charge? What value do they deliver? This gives you a realistic pricing range for what your audience is accustomed to paying.
The hard truth: If you can't find evidence that people are willing to pay — through current spending, search intent, or market comparisons — your idea might be a "nice to have" rather than a "must have." Nice-to-haves don't build businesses.
Killing bad ideas early
This is the most important skill in product development, and AI makes it dramatically easier. The goal is to spend hours, not months, discovering that an idea won't work.
Here's your rapid kill checklist. Ask AI to evaluate each point:
- Market too small. If the total addressable market is under £1 million, it's a hobby, not a business.
- Problem not painful enough. If people are mildly annoyed but not actively seeking solutions, they won't pay.
- Too many good alternatives. If 5+ well-funded competitors already solve this well and customers are satisfied, the window is closed.
- Can't reach the audience. If your target customers don't congregate anywhere you can reach them affordably, marketing costs will kill you.
- Timing is wrong. Sometimes an idea is too early (infrastructure doesn't exist yet) or too late (market is saturated). AI can help you assess where the market stands.
Run your top 3 ideas through this checklist. Be ruthless. The ideas that survive are the ones worth taking to tomorrow's competitive analysis.