Beginner Level 2: Finding Great Ideas
Chapter Overview
Step 1: Establish Criteria — What Makes Users Willing to Pay
Why is this chapter important?
Some might find it strange: "Isn't this a course teaching Vibe Coding? Why learn 'finding needs' first? Can't we just start coding?"
Indeed, many programming courses on the market teach you to build projects directly: make a Todo List, a calculator, a personal blog... These projects can help you get familiar with syntax and tools, but the problem is:
Wrong direction, the deeper you go, the more wrong you become.
Imagine:
- You spend two weeks building a "calendar management system," but there are already 100 better ones on the market
- You make a "calorie photo calculator," but users uninstall it after one use
- You create a "personal expense tracker," but even you can't be bothered to use it
After completing these projects, can you put them on your resume? Probably not, because they don't solve real problems or create real value.
The harsher truth is: since we're investing time in learning, why not aim for better results?
Since Vibe Coding lets us quickly turn ideas into products, we should learn to find ideas worth building. Train yourself in the most practical way — not by making "practice projects," but by making "products people want to use."
That's why we need to learn "finding great ideas" first.
In my opinion, time is precious. If you're going to do something, do it right, otherwise why not just play? As a responsibility, I'll do my best to support you in achieving excellence.
Even if no one believes you can do well, I'll steadfastly hope for your success. You've chosen vibecoding to build products, so let's see how far you can go!
Opening: The Story of Independent Developer Xiao Ming
Xiao Ming is a programmer with three years of experience. One day he suddenly thought: why not make a fitness APP to help users create workout plans and record training data? This idea excited him — he finally found a project he could work on.
Over the next year, Xiao Ming poured almost all his spare time into it. He built a fully-featured APP — course modules, check-in systems, community features, data analysis — everything it should have. The interface looked pretty good too, at least he thought so.
On launch day, Xiao Ming was full of anticipation. He spent quite a bit on promotion, and in the first month, 50,000 people downloaded it. Looks like a good start, right?
But problems soon emerged. After downloading, users would uninstall after one use. The 7-day retention was only 5%. He added some paid features, but almost no users were willing to pay. What frustrated him more was that mature products like Keep, Bohe Health, and FitTime had more complete features and better content — why would users switch to his APP?
After a year, Xiao Ming lost 200,000 yuan.
He sat in front of his computer, looking at the dismal data in the backend, with only one question in his mind: My APP is pretty good, why does nobody use it? Even more, why won't anyone pay for it?
Xiao Ming's failure wasn't because his technology was bad, nor because the product was poorly made. Honestly, his APP had comprehensive features and a nice interface.
The problem was at the starting point.
He never asked the most basic question: Do users really need this?
He saw the fitness APP market was huge, Keep was valued at hundreds of millions, and thought this was a great opportunity. But he didn't clarify a few things: Why do users need another fitness APP? Compared to Keep, what's my differentiation? Are users willing to pay for this?
Wrong direction, the deeper you go, the more wrong you become. He spent a year making a wrong direction increasingly perfect, only to move further from success.
What we'll do in this chapter
In this chapter, let's help Xiao Ming review what happened. Let's see where his problem really was, and then together find product directions that people are actually willing to pay for.
We'll proceed in three steps:
Act 1: Find Real Needs — First understand what kind of needs users are willing to pay for
Act 2: Dig Out Great Ideas — Learn to mine valuable business opportunities from ordinary ideas
Act 3: AI Dialogue Refinement — Use AI to turn ideas into actionable product plans
Act 1: Finding Real Needs
Xiao Ming was frustrated but didn't give up. He started reflecting on a question: What kind of needs are users actually willing to pay for?
Xiao Ming's Confusion: Why Won't Users Pay?
He went to find a few friends who had used his APP, wanting to hear their honest thoughts.
Friend A said: "Your APP is pretty good, but I'm already using Keep. Why would I switch?"
Friend B said: "You want me to record every workout — that's too much trouble. I'm too lazy to do that."
Friend C was more direct: "The free features are enough. Why would I pay?"
These answers made Xiao Ming suddenly understand where the problem was.
First problem: Users won't switch because existing solutions are already good enough. Mature products like Keep already have comprehensive features, and users have formed habits. The switching cost is high. Why would users switch to your similar product?
Second problem: Users aren't willing to change habits. Recording workouts is too troublesome for users. If a product requires users to change more than 3 habits, it will likely fail.
Third problem: Too many free alternatives. Your features are too generic with no unique value. Users can't find a reason to pay.
What is a Real Need?
Xiao Ming started studying successful products that make users willing to pay. He found a common point: these products don't solve "I think it's useful" needs, but needs that users are willing to pay for, willing to change behavior for, and willing to endure inconvenience for.
In other words, real needs are voted on by users with their feet, not dreamed up by product managers.
Case Studies: Products That Make Users Pay
Xiao Ming studied several successful cases, trying to understand what pain points they really captured.
Meicai: Let Small Restaurant Owners Sleep Better
On the surface, what Meicai does is simple: help restaurants buy vegetables. But if you think carefully, why would restaurant owners use it?
Because small restaurant owners have to get up at 4 AM every day to go to wholesale markets. It's exhausting, and they often get cheated. What Meicai does isn't simple "e-commerce selling vegetables" — it restructured the entire supply chain, letting small restaurant owners sleep better.
The more painful the pain point, the stronger the willingness to pay. The time and energy saved is more valuable than the money saved on vegetables.
Xiaohongshu: Solving Choice Paralysis
On the surface, Xiaohongshu is "sharing overseas shopping experiences." But why are users willing to spend time reading notes on it?
Because facing a sea of products, users don't know what's worth buying and what isn't. They need someone they trust to help them filter, save time, and avoid pitfalls.
What Xiaohongshu really solves are two deep pain points: choice paralysis and lack of trust. Users are willing to pay for "saving time" and "avoiding pitfalls" — that's why Xiaohongshu succeeded.
After seeing these cases, Xiao Ming had an important discovery.
Users never pay for "features" — they pay for "solving fear" and "eliminating anxiety." Meicai solves small restaurant owners' fear of the hardship of early morning procurement. Xiaohongshu solves users' fear of buying the wrong things.
Fear drives payment. Anxiety drives action.
Three Layers of Needs: Pain Points, Delight Points, Itch Points
Xiao Ming researched further and found that user needs can be divided into three types:
Pain Point — Fear Driven
Essence: Problems users are currently experiencing that make them feel pain, anxiety, or inconvenience. Not solving them causes significant discomfort, or even threatens survival or safety.
Examples:
- Diabetics don't know how many carbs will spike their blood sugar (Fear: Health threat)
- Small restaurant owners get up at 4 AM to go to wholesale markets (Fear: Survival hardship)
Key: Users are willing to pay for this because not solving it is "very painful."
Delight Point — Instant Gratification
Essence: Users have a need that can be immediately satisfied, producing instant pleasure.
Examples:
- Food delivery in 30 minutes (Instant satisfaction of hunger)
- One-click generation of beautiful PPT (Time-saving and effort-saving delight)
Key: Making users "delighted" is key to retention, but as a standalone payment point it's weak.
Itch Point — Virtual Self
Essence: Users want to become better, cooler, more refined, but it's not necessary. Satisfying it makes them happy; not satisfying it is fine too.
Examples:
- Recording how much water you drink each day (Imagined disciplined life)
- Using AI to add artistic filters to photos (Imagined artistic taste)
Key: Users have weak willingness to pay for "itch points" because not solving it doesn't matter.
What's the correct priority ranking? A good suggestion is: Pain Points > Delight Points > Itch Points
Why?
- Pain points are survival needs: Not solving them means death (or great discomfort). Users have to pay. They're "painkillers."
- Delight points are instant rewards: Make users delighted, and they'll come. They're "heroin" (in the positive sense of addictive mechanisms).
- Itch points are desire satisfaction: Nice to have, easiest to cut. They're "vitamins" or "luxury goods."
Key Insight: Many product managers make the mistake of marketing itch point products using pain point methods.
For example: "Recording water intake will make you healthier" — drinking water is indeed healthy, but not recording it won't make you unhealthy. This is packaging an itch point as a pain point. Users won't buy it.
5-Step Method to Validate Real Needs
Xiao Ming thought: When I have an idea, how do I quickly judge if it's worth investing in?
He learned the 5-step judgment method commonly used by product managers (detailed content in Appendix A):
Step 1: Talk directly with real users to understand their current approach
Find 10 target users. Ask them: "How do you currently solve this problem?" If users are already using some method, the problem really exists. If users say they don't need to solve it, it might not be a real need.
Step 2: Analyze users' existing alternatives and find your advantages
Users might currently use other products, Excel, rely on memory, or just endure without solving. You need to figure out the drawbacks of these solutions. Your product needs to be much better than them for users to switch.
Step 3: Test if users are willing to pay for your product
Do pre-sales or collect deposits. Count the percentage of users willing to pay deposits (earning money early indicates correct need):
- Over 10%: Need is real, worth investing
- 5% to 10%: Need exists but needs refinement
- Below 5%: Need might not be valid
Step 4: Estimate how big this market is and if it can make money
Calculate three numbers: Total target users × Willingness to pay × Average transaction value. Multiply them to get market size. If the market is too small, it might not be worth doing.
Step 5: Think about what moat your product has to prevent copying
Consider these barriers: Technical difficulty, network effects, brand, cost advantages. These can help you maintain competitiveness long-term.
Act Summary: Xiao Ming's Takeaways
Standards for Real Needs
- The most important standard is users are willing to pay.
- Users are willing to change behavior for it.
- Without a solution, users would suffer significant loss.
Avoid Fake Needs
- Itch points aren't pain points; they can't be treated as real needs.
- Markets that are too small can't support a business model.
- Solutions more complex than the problem will be abandoned by users.
Priority Ranking
- The real priority is: Pain Points > Delight Points > Itch Points.
Act Output
- I understand what real needs are.
- I've mastered the three-layer classification of needs: pain points, delight points, itch points.
- I've learned the 5-step judgment method to validate needs.
Act 2: Digging Out Great Ideas
Xiao Ming now knows what real needs are, but he still doesn't know where to start. He can't just imagine a need out of thin air, right?
He decided to start from what he knows best — the people and things around him.
Start from Yourself: Xiao Ming's Sister
Xiao Ming thought of his sister. She just had a baby and keeps complaining about having no time to exercise. She can't lose the belly fat and is very anxious about it.
One day Xiao Ming asked her: "How are you currently solving the fitness problem?"
His sister sighed and said: "I follow Keep, but those exercises aren't suitable for postpartum bodies. After doing them, my lower back hurts even more. Go to a gym? No one to help watch the baby. Hire a personal trainer? One session costs 300-500 yuan, too expensive. Exercise blindly on my own? I'm afraid of getting injured."
After hearing this, Xiao Ming felt this might be the real need he was looking for.
His sister's troubles are actually quite specific: Fragmented time, needs to care for the baby, no uninterrupted time for exercise; Physical limitations, diastasis recti, pelvic floor muscle laxity, can't do intense exercise; Psychological anxiety, body shape changed, worried husband will dislike it, socially insecure; Information is too chaotic, too much information online, don't know what exercises are suitable for postpartum; And loneliness, no one understands their situation, lack of peer support.
These are all real pain points, not "nice to have" itch points.
Horizontal Segmentation: Needs of Different User Groups
Xiao Ming realized that the "fitness APP" idea was too broad. He wanted to help everyone exercise, but the problem is, everyone's needs are different.
He did a horizontal segmentation, dividing "people who want to exercise" into several categories (detailed method in Appendix B):
Fitness muscle-building crowd needs precise protein intake calculation, manual recording is too troublesome, their willingness to pay is high, pursuing efficiency. Diabetics must strictly control carbs, but it's hard to estimate when eating out, this is a rigid need, willing to pay, high repurchase rate. Postpartum moms want to recover their figure but don't have time to calculate, need simple solutions, time-sensitive, need one-stop service. Food delivery crowd eats takeout every day not knowing how many calories consumed, this is a high-frequency scenario, but medium willingness to pay. Graduate exam students need efficient study tools but don't know what to use, this is a rigid need, but low average transaction value.
Xiao Ming chose the "postpartum moms" group. Why?
First, he himself is a user — his sister is a postpartum mom, so he naturally understands this group's pain points. Second, the pain point is very painful — postpartum recovery anxiety is real, not a "nice to have" itch point. Third, strong willingness to pay — moms are willing to spend money to recover their figure. Fourth, relatively less competition — there's no product specifically for postpartum moms on the market.
Product Manager's Segmentation Logic
Why is segmenting user groups so important?
Because generic tools are hard to win. Big platforms have already occupied the "generic" market, and it's hard for you to surpass them in features. Specific user groups have more painful needs — postpartum moms' need for exercise is a rigid need, while regular exercisers just think "it would be nice." Serving a small group well is easier than pleasing everyone to build reputation. Specific user groups' pain points are more concrete, and they're more willing to pay for solutions.
Vertical Deep Dive: Complete User Scenarios
After finding the user group, Xiao Ming didn't stop at the single function of "postpartum exercise." He wanted to understand users' complete scenarios more deeply (detailed method in Appendix C).
He observed his sister's day.
6 AM, the baby just fell asleep, sister has 30 minutes free. She wants to exercise but fears waking the baby, and doesn't know what movements are safe.
10 AM, sister is holding the baby to sleep, her lower back is sore. She wants to do some recovery exercises but her hands are occupied.
3 PM, baby is sleeping, sister wants to exercise. But her body is tired, doesn't know if she can still do it.
8 PM, sister finally has time but is very anxious. Looking at herself in the mirror, feeling like life is over, secretly crying while looking at old photos.
Xiao Ming discovered that his sister's pain point isn't "no fitness courses" but "fear and anxiety about postpartum recovery."
Product Manager's Scenario Thinking
Many people think pain points are just functional requirements, but they're not. Pain points are emotions in scenarios plus willingness to pay.
When postpartum moms face their changed bodies in the mirror, the real pain point isn't "not knowing how to exercise" but fear — worrying about not recovering well, leaving sequelae; Anxiety — looking at themselves in the mirror, feeling like life is over; Helplessness — not knowing where to start, no one to guide; Loneliness — others give birth easily, but I have to recover for so long.
Good product design solves emotions, not just functions. Behind emotions is the user's motivation to pay.
Value Reconstruction: From "Fitness APP" to "Postpartum Mom Recovery Assistant"
Based on the above analysis, Xiao Ming redesigned this product.
Reconstructed Product Concept: "Postpartum Mom Recovery Assistant"
Core Positioning: Not just a fitness tool, but a "personal rehabilitation coach + psychological supporter" for postpartum moms
Core Features:
Fragmented Training:
- Each session only needs 10-15 minutes
- Can exercise when baby is sleeping
- Provides movements that "can be done while holding the baby"
Postpartum-Specific Courses:
- Graded by postpartum stage (0-3 months, 3-6 months, 6+ months)
- Specialized training for diastasis recti, pelvic floor muscle repair
- Every movement has "postpartum precautions" reminders
AI Movement Correction:
- Phone camera recognizes movements
- Real-time reminders like "knees too bent," "back should be straight"
- Avoid injury from incorrect movements
Psychological Support Community:
- Private community only for postpartum moms
- Share recovery progress, encourage each other
- Professional psychological counselors on board
Personalized Plans:
- Customized based on delivery method (natural/C-section), physical condition
- Considers special needs during breastfeeding
Business Model:
- Basic courses free
- Advanced courses: 99 yuan/month (includes AI movement correction, personalized plans)
- One-on-one coaching: 299 yuan/month (online guidance)
- Community membership: 199 yuan/year (includes psychological support, expert Q&A)
Competitive Barriers:
- Professionalism: Partnership with postpartum recovery institutions, medical endorsement
- Community stickiness: Postpartum moms' emotional connections are strong
- Data accumulation: More user body data means more precise plans
Market Size:
- China has about 10 million newborns annually
- Postpartum recovery market is about 50 billion yuan
- Target: Serve 1% of postpartum moms = 100,000 users
- ARPU (Average Revenue Per User): 500 yuan/year
- Potential revenue: 50 million yuan/year
Comparing the original idea with the reconstructed concept:
| Dimension | Original Idea | Reconstructed |
|---|---|---|
| Target Users | All fitness groups (broad) | Postpartum moms (precise) |
| Pain Point Solved | Recording workouts (itch point) | Postpartum recovery anxiety (pain point) |
| Competitive Barrier | Technology (easily copied) | Professionalism + Community + Data |
| Willingness to Pay | Low (many free alternatives) | High (rigid need + emotional value) |
| Expansion Space | Limited | Can expand to pregnancy, pre-pregnancy |
This is the evolution from "a feature" to "a product people pay for."
More Examples: From Ordinary Ideas to Great Ideas
Xiao Ming found this method very useful. He used the same method to analyze several other examples, wanting to see if this method is universally applicable (detailed cases in Appendix D).
Example 1: From "Calorie Measurement" to "Diabetics Eat with Peace of Mind"
The ordinary idea is photo recognition of food calories, helping people who want to lose weight control their diet. But the problem is there are already mature products like Bohe Health and MyFitnessPal on the market.
Xiao Ming did a horizontal segmentation and found the diabetic group interesting: They must strictly control carbs, but it's hard to estimate when eating out. Deep diving into their scenarios: Before meals, don't know if this dish can be eaten, worried about blood sugar spikes; During meals, need real-time reminders "how many carbs you've already had"; After meals, need to record blood sugar changes to see the relationship with diet.
The reconstructed product is called "Diabetics Eat with Peace of Mind," positioned as a "dietary safety assistant" for diabetics.
Example 2: From "News Assistant" to "Investment Research Intelligence Officer"
The ordinary idea is aggregating news from various platforms, saving the trouble of opening them one by one. But Toutiao, Tencent News, etc., already do this well.
Xiao Ming then did horizontal segmentation and found that financial analysts have a special need: they must track dynamics in specific industries, but information is too fragmented. He further deep-dived into their scenarios: in the morning they check overnight U.S. market moves and exchange-rate changes; during the day they track announcements and industry news for portfolio companies; in the afternoon they research potential targets and need large amounts of sector information.
The reconstructed product is called "Investment Research Intelligence Officer," positioned as an "information radar and decision assistant" for financial professionals.
Example 3: From "Campus Second-Hand Platform" to "Graduation Clearance Assistant"
The ordinary idea is a campus second-hand marketplace. But Xianyu and Zhuanzhuan are already very mature.
After horizontal segmentation, Xiao Ming found that graduates have a special need: they have too many things, and selling one by one is too troublesome. Deep-diving into their scenarios: they must leave campus within a week before graduation and do not have time to sell slowly; they do not know who needs their items; bargaining, delivery, and payment collection are all too cumbersome.
The reconstructed product is called "Graduation Clearance Assistant," positioned as a "move-out asset manager" for graduates.
Act 2 Summary: Xiao Ming's Takeaways
Through Act 2, Xiao Ming understood:
1. Start from yourself
- You yourself are a user, so you naturally understand that group's pain points
- Interest is the best starting point, and passion is the best driving force
2. Segment users horizontally
- Do not serve "everyone"; find "the segment with the strongest pain"
- The more specific the segment, the more opportunity and stronger willingness to pay
3. Deep-dive scenarios vertically
- Describe the complete user journey: before use, during use, after use
- Find emotional touchpoints: fear, anxiety, helplessness, loneliness...
4. Reconstruct value
- Upgrade from a "feature" to a "solution"
- Upgrade from a "tool" to an "assistant/manager/companion"
📦 Act Output:
- Found one precise target user group (postpartum moms)
- Understood users' complete scenarios and real emotions
- Reconstructed the product concept with a clear differentiation strategy
Act 3: AI Dialogue Refinement
Xiao Ming now had a clear product direction: a postpartum mom recovery assistant. But he still did not know exactly how to execute it, where to start, or how difficult the technical implementation would be.
He decided to use AI to help refine the concept and turn the idea into an actionable plan.
Round 1: Present the raw idea
Xiao Ming told AI his idea: "I want to build a postpartum mom recovery assistant app to help postpartum moms recover their figure. But I worry about technical implementation difficulty, especially the AI movement-correction feature. Can one person do this?"
Round 2: AI helps plan the MVP
AI replied: "Great question! Let's create an MVP (Minimum Viable Product) plan."
AI suggested a three-phase plan. Phase 1 is 1-2 months, and the goal is demand validation. Do not build a full app yet; first build a WeChat mini program that only provides postpartum-specific courses (videos) and a check-in community. Use manual guidance for movement feedback: users upload videos and coaches reply. The goal is to validate whether postpartum moms are willing to pay.
Phase 2 is 3-6 months. If Phase 1 validates successfully, then add core features. Develop AI movement correction, possibly with existing SDKs such as Baidu human-pose recognition. Add personalized plans and optimize community functions.
Phase 3 is 6-12 months, for scaling. Build an independent app, cooperate with postpartum recovery institutions, and expand to pregnancy and pre-pregnancy scenarios.
For technical implementation, AI suggested using existing AI capabilities for movement correction, such as Baidu or Tencent APIs, instead of building from scratch, to reduce cost. In the early stage, use a hybrid mode of manual plus AI, then transition gradually.
For startup cost, mini program development is about 10,000-20,000 RMB if outsourced, or do it yourself with AI IDE. For content creation, cooperate with postpartum recovery coaches. For promotion, start from mom groups and Xiaohongshu.
Validation KPI: 100 users in the first month and a 10% paid conversion rate. If reached, demand is real and you continue investing; if not, adjust direction in time.
Round 3: Xiao Ming raises concerns
After thinking, Xiao Ming asked again: "I am worried about content production. Postpartum recovery courses require professional guidance, and I do not have a medical background. How can I ensure course quality?"
Round 4: AI provides solutions
AI replied: "This is a common concern for technical founders, but there are solutions."
Solution 1 is to collaborate with professionals. Work with postpartum recovery coaches or hospital nutrition doctors. You provide the technology and product; they provide professional content. Use a revenue-sharing model.
Solution 2 is to integrate high-quality existing content. In the early stage, use public postpartum recovery videos, such as from YouTube or Bilibili. Do content review and curation first, then produce original content later.
Solution 3 is user-generated content. Encourage experienced moms to share their recovery methods, and use community voting to filter quality content, gradually building a content ecosystem.
AI recommended starting with Solution 1. Specific operation: find 2-3 postpartum recovery coaches and discuss cooperation; you build the product, they provide courses. Revenue split: you take 70%, they take 30%. This ensures quality while reducing cost. Early-stage course production cost can be zero with revenue sharing; you only invest development time and promotion cost.
My suggestion: start with Solution 1
Specific actions:
- Find 2-3 postpartum recovery coaches
- Propose cooperation: you build the product, they provide courses
- Revenue split: you take 70%, they take 30%
- This ensures content quality and lowers cost
Early-stage cost:
- Course production: 0 RMB (revenue-share model)
- You only need to invest development time and promotion cost
:::
Round 5: Xiao Ming asks about promotion
Xiao Ming had one final concern: "Will promotion cost be high? How do I find postpartum moms?"
Round 6: AI provides promotion strategy
AI replied: "This group is actually easy to find, and promotion cost can be very low."
The most recommended channel is Xiaohongshu. Search keywords like "postpartum recovery" and "diastasis recti," find related creators, and DM for collaboration. Offer "1 month free trial" in exchange for promotion, with near-zero cost.
Second is mom groups. Search WeChat groups and QQ groups. Join under the name of "postpartum recovery experience sharing," share useful content, do not post direct ads, and gradually build trust.
You can also cooperate with hospital obstetrics departments by providing free postpartum recovery guidance and distributing flyers in hospitals, with only a few hundred RMB printing cost. Or cooperate with maternal-and-infant stores, place promotional materials, and provide trial cards with purchases, with only trial-card production cost.
Validation metrics: in the first month, 100 users and 10 paid users (10% conversion rate), total promotion cost under 1000 RMB, and customer acquisition cost under 10 RMB per user. If these metrics are met, demand is real and you can continue investing.
Final: Xiao Ming now has a clear plan
After 6 rounds of dialogue, Xiao Ming finally had a clear plan.
Phase 1 (1-2 months): build a WeChat mini program, cooperate with 2-3 postpartum recovery coaches (revenue share), provide only postpartum-specific courses (videos) and a check-in community, and use manual movement guidance. Target: 100 users and 10% paid conversion.
Phase 2 (3-6 months): if Phase 1 validates successfully, continue investing. Add AI movement correction, personalized plans, and optimize community features.
Phase 3 (6-12 months): develop an independent app, cooperate with postpartum recovery institutions, and expand to pregnancy and pre-pregnancy phases.
Startup cost is very low: development done by yourself using AI IDE (0 RMB), content with coach revenue sharing (0 RMB in early stage), and promotion via Xiaohongshu plus mom groups (under 1000 RMB). Total cost under 1000 RMB.
The 5-step method for AI dialogue refinement
From this case, Xiao Ming summarized a standard AI dialogue workflow (see Appendix E for details).
Step 1: Present the raw idea. Describe your initial idea, even if rough. Tell AI your concerns, such as heavy competition or unclear differentiation.
Step 2: Ask AI to plan the MVP. What should the minimum viable product include? How many phases? What are the goals in each phase? How difficult is implementation?
Step 3: Raise your concerns. Technical difficulty? Content production cost? Promotion cost? User acquisition difficulty? Tell AI all your concerns.
Step 4: Ask AI for concrete solutions. AI will provide specific suggestions for your concerns. Compare options and choose the best one. Estimate costs.
Step 5: Finalize the plan. Organize a clear action plan and set validation metrics. If targets are not met, adjust in time.
Prompt template:
I want to build a [product concept],
but I am worried about [your concern].
Please help me:
1. Plan an MVP
2. Give concrete technical implementation suggestions
3. Estimate cost
4. Set validation metricsAct 3 Summary: Xiao Ming's Takeaways
Through Act 3, Xiao Ming understood three things.
First, use AI dialogue to refine product concepts. Do not expect one conversation to produce a perfect answer; iterate through multiple rounds. Tell AI your observations, experiences, and feedback from people around you. If AI suggestions are unreasonable, point it out in time. Always end with a concrete action plan.
Second, MVP core principles. Keep it minimal, and only build the core function. Make it verifiable, so you can quickly validate whether demand is real. Keep it low cost, and validate with the smallest possible investment.
Third, validation metrics. Paid conversion > 10% means demand is real and worth investment. Paid conversion 5-10% means demand exists but needs refinement. Paid conversion < 5% means demand does not hold and direction should be adjusted.
📦 Chapter Output:
- A clear MVP plan
- A known technical implementation path
- Defined validation metrics
Final Act: Your Action
Memory mantra
Start from one person, one thing, one entry point. Segment horizontally, dig vertically, refine through AI dialogue, and only build after five-step validation.
Explanation:
- One person: Start from yourself because you naturally understand this group
- One thing: Focus on one concrete thing and do not be greedy
- One entry point: Find a sharp entry point, and the more segmented, the better
- Horizontal segmentation: Find users with strongest willingness to pay
- Vertical deep dive: Understand users' complete journey
- AI dialogue: Refine product concepts with AI dialogue
- Five-step validation: Use the five-step method to validate demand authenticity
Post-class exercise
Choose one small annoyance from your daily life and expand it using this chapter's method:
Exercise Task
1. Describe this annoyance (in one sentence)
- Example: "I want to build a bookkeeping app to help users record spending."
2. Horizontal segmentation: find 3 user groups that may have different needs
- Example: small business owners, parents of overseas students, freelancers
3. Select one group, then deep-dive vertically: describe their complete scenario and real emotions
- Example: scenario of overseas-student parents - they want to know how much their child spends abroad, but the child does not tell them
4. Reconstruct product concept: evolve from "one feature" into "one solution"
- Example: "Overseas Spending Steward" - not just bookkeeping, but giving parents confidence and visibility into overseas spending
5. Evaluate your idea with the validation checklist (see Appendix F)
Share your analysis in the community and discuss with other learners!
Appendix: SOP Methodology
Appendix A: 5-Step judgment method for need analysis
When you have an idea, how can you quickly judge whether it is worth investing in?
Step 1: User validation - find 10 target users
Do not ask: "Will you use my product?" (false-positive rate is around 90%)
Ask instead:
- "How do you currently solve this problem?" (understand real behavior)
- "How many times did this problem bother you in the last week?" (understand frequency)
- "How much money/time did you spend to solve it?" (understand willingness to pay)
- "If there is a solution but it requires changing habits, are you willing?" (understand change cost)
Decision criteria:
- If more than 3 users say "this gives me headache every day" - it may be a pain point
- If users say "interesting, but not urgent" - most likely an itch point
- If users say "I currently use XX, but not satisfied" - there is opportunity
Key question: what method do users currently use to solve this problem?
| Alternative Type | Description | Opportunity Assessment |
|---|---|---|
| No alternative | Users silently endure | Big opportunity, but market education is required |
| Using clumsy methods | Excel, manual work, multi-person collaboration | Good opportunity, users want better solutions |
| Combining multiple tools | Tool A + Tool B + Tool C | Good opportunity, integration has value |
| Using mature products | But users are unsatisfied | Opportunity exists, but differentiation is needed |
| Using mature products | Users are satisfied | Very small opportunity unless there is disruptive innovation |
What is "disruptive innovation"?
Simple definition: not making products incrementally better, but serving previously overlooked user groups with a simpler/cheaper approach.
Examples:
- Traditional phones -> smartphones (not just more functions, but a completely different interaction model)
- Traditional taxis -> Didi/Uber (not better cars, but on-demand ride calling anywhere)
- Traditional bookstores -> e-books (not more books, but easier carrying and purchasing)
Key point: disruptive innovation often starts from low-end markets or new user groups, and then gradually moves upward.
Cases:
- Diabetics currently control diet by "experience + guessing" (very clumsy method) -> big opportunity
- Ordinary dieters use Bohe Health (mature product, medium satisfaction) -> opportunity for vertical segmentation
- Students use WeChat groups for second-hand trading (multiple tools stitched together) -> opportunity for integration
Most effective method: presale or deposit
Steps:
- Create a simple landing page and describe your product concept
- Put a "presale" or "reservation" button
- See how many people are willing to pay (even 1 RMB counts)
Decision criteria:
- Users willing to pay deposit > 10%: demand is real and worth doing
- 5%-10%: demand exists but needs refinement
- < 5%: demand may not be valid, or product concept has issues
Note: many people say "I will buy." The people who actually pay are your real target users.
Simple formula:
Potential market size = target user count × willingness to pay × average order valueCase: campus second-hand trading platform
- Target users: 40 million college students in China
- With second-hand trading demand: 50% = 20 million
- Willing to use platform: 10% = 2 million
- Annual transaction frequency: 2 times
- Platform commission: 5%
- Average order value: 100 RMB
- Potential market size = 2,000,000 × 2 × 100 × 5% = 20 million RMB/year
Decision criteria:
- Market size > 1 billion RMB: large track, worth pursuing
- 100 million-1 billion RMB: medium/small track, possible but ceiling is visible
- < 100 million RMB: niche market, suitable for side business or a small-and-beautiful business
Key question: if the product succeeds, what if others copy it?
Common moat types:
| Moat Type | Description | Example |
|---|---|---|
| Network effects | More users -> more product value | WeChat, Didi |
| Data accumulation | More data -> better algorithm | Toutiao, Douyin |
| Brand cognition | Occupying user mindshare | Coca-Cola, Nike |
| Scale effects | Larger scale -> lower costs | JD logistics, Amazon |
| Technical patents | Core technology barriers | Huawei, DJI |
| Switching costs | High migration cost for users | Enterprise software, operating systems |
Early-stage reality:
- Most early projects do not have clear moats
- But that is fine; the key is to move fast
- Occupy market first, then build barriers
Appendix B: Horizontal user-segmentation method
Do not try to serve "all XX users." Instead, find one specific group with sharper and more concrete needs.
Step 1: List all possible segmented user groups
For your product concept, list all possible user groups.
Step 2: Evaluate the business value of each group
| Evaluation Dimension | Description |
|---|---|
| Pain intensity | Is this group's need a pain point or itch point? |
| Willingness to pay | How much are they willing to pay for a solution? |
| Market size | How many people are in this group? |
| Competition level | Are current solutions satisfactory? |
| Your understanding of this group | Do you understand this group? Do you have access channels? |
Step 3: Choose one group for deep analysis
Choose the one that is:
- most painful
- highest willingness to pay
- best understood by you
- relatively less competitive
Segmentation Example
Product concept: bookkeeping app
| Segmented Group | Pain Point | Willingness to Pay | Market Size | Competition |
|---|---|---|---|---|
| Ordinary office workers | Recording is troublesome | Low | Large | High |
| Small business owners | Personal/company spending is mixed up | High | Medium | Medium |
| Freelancers | Unstable income, need cash-flow forecast | High | Medium | Medium |
| Parents of overseas students | Want to know child's spending but child does not say | High | Small | Low |
Chosen segment: parents of overseas students (strongest pain point, high willingness to pay, relatively low competition)
Appendix C: Vertical scenario deep-dive method
After finding the user group, do not stop at a single feature. You need to understand the user's complete scenario.
Step 1: Describe one full day of the user
From morning to night, describe the complete scenario in which the user interacts with your product.
Step 2: Analyze pain points in each scenario
In each scenario, what problems does the user encounter? What emotions appear?
Step 3: Find emotional touchpoints
Fear, anxiety, helplessness, loneliness, anger, regret...
Step 4: Reconstruct value
Based on scenarios and emotions, reconstruct product value.
Deep-Dive Example
User group: postpartum moms
| Time | Scenario | Pain Point | Emotion |
|---|---|---|---|
| 6 AM | Baby just fell asleep, 30 minutes free | Do not know what movement is safe | Fear |
| 10 AM | Holding baby to help sleep, lower back soreness | Hands occupied, wants recovery exercise | Anxiety |
| 3 PM | Baby sleeping, wants to exercise | Body is tired, unsure if can continue | Helplessness |
| 8 PM | Finally has time | Sees body in mirror and feels life is over | Depression |
| Long term | No one understands | Feels like only self suffers this much | Loneliness |
Reconstructed value: upgrade from "fitness tool" to "rehab coach + psychological supporter"
Appendix D: More examples from ordinary ideas to great ideas
Example 1: From "bookkeeping app" to "Overseas Spending Steward"
Ordinary idea: automatic bookkeeping app, connecting bank cards to auto-categorize spending
Problem: there are already SuiShouJi, WaCai, Alipay bills...
Horizontal segmentation:
- Parents of overseas students: want to know how much their child spends abroad and whether they overspend
Vertical deep dive:
- Pain point is not bookkeeping but "loss of control" - do not know how much the child spends or where money goes
- Scenario: every month parents see credit-card bills, but the child never proactively explains spending
Reconstructed concept: "Overseas Spending Steward" - not only bookkeeping, but letting parents "have clear visibility" on overseas spending
Core features:
- Real-time child spending sync
- Overspending alerts
- Monthly spending analysis reports
- Peer comparison among similar students ("your child spends 20% above average")
Example 2: From "Pomodoro tool" to "Remote Work Proof"
Ordinary idea: Pomodoro app to help users focus
Problem: phones already have screen-time stats, plus Forest and Pomodoro Todo...
Horizontal segmentation:
- Remote workers: need to prove to managers that they are truly working
Vertical deep dive:
- Pain point is not "cannot focus," but "trust crisis" - if manager cannot see me, how do I prove I am working?
- Scenario: every day after work, manager asks "how was your progress today?" and there is no proof
Reconstructed concept: "Remote Work Proof" - helping remote workers build trust with employers
Core features:
- Automatic work-time tracking
- Productivity reports
- Screen activity summaries (privacy-protected)
- Auto-generated daily work report sent to supervisor
Example 3: From "second-hand book trading" to "Picture Book Library"
Ordinary idea: second-hand book trading platform
Problem: there are already Duozhuayu, Xianshu, and Kongfuzi used-book marketplaces...
Horizontal segmentation:
- Mom users: children's picture books become idle after reading, but buying new books is expensive
Vertical deep dive:
- Pain point is not "books are expensive," but "short lifecycle of picture books" - books for age 3 are not read at age 4
- Scenario: home is full of picture books that children no longer read, but throwing them away feels wasteful
Reconstructed concept: "Picture Book Library delivered to your home" - not selling used books, but providing "rental of usage rights"
Core features:
- Picture book subscription (mail 5 age-appropriate books each month, return after reading, then rotate new ones)
- Reading progress tracking
- Age-appropriate recommendations
- Sterilization guarantee
Appendix E: 5-step method to refine product concepts via AI dialogue
Use multi-round AI dialogue to gradually refine ordinary ideas into precise, executable product concepts.
Operation:
- Describe your initial idea (even if rough)
- Tell AI your concerns (heavy competition, unclear differentiation, etc.)
Prompt:
I want to build [product concept],
but I found [problem/concern].Operation:
- Ask AI to create a minimum viable product plan
- Discuss implementation difficulty and costs
- Define validation metrics
Prompt:
Please help me:
1. Plan an MVP
2. Provide concrete technical implementation advice
3. Estimate cost
4. Define validation metricsOperation:
- Technical difficulty?
- Content production cost?
- Promotion cost?
- User acquisition difficulty?
Prompt:
I am worried about:
1. [Concern 1]
2. [Concern 2]
3. [Concern 3]Operation:
- Provide concrete solutions for your concerns
- Compare multiple options and choose the best
- Estimate costs
Prompt:
Please provide concrete solutions for my concerns.Operation:
- Organize a clear action plan
- Set validation metrics
- If metrics are not met, adjust direction quickly
Prompt:
Please help me organize a clear action plan.Key techniques
- Multi-round dialogue: do not expect a perfect answer in one round; iterate
- Provide information: tell AI your observations, experiences, and people-around-you feedback
- Challenge AI: if AI suggestions are unreasonable, call that out in time
- Focus on execution: always end with a concrete action plan
Appendix F: Need validation checklist
Before deciding to invest development time, validate your idea with the checklist below - the core question is always: will users pay for this?
Need Validation Checklist
1. User profile clarity
- ☐ Can you describe your target user in one sentence?
- ☐ Can you state what alternative they currently use?
- ☐ Can you describe specific details of their usage scenario?
- ☐ Does this user group have payment capability?
2. Pain intensity evaluation
- ☐ What cost do users pay now to solve this problem? (time/money/effort)
- ☐ If they do not solve it, what consequence follows?
- ☐ Are users actively seeking solutions?
- ☐ How much are users willing to pay for this?
3. Solution differentiation
- ☐ Compared with existing solutions, what is your advantage?
- ☐ Is that advantage strong enough to make users switch?
- ☐ How hard is it for big platforms to copy your feature?
- ☐ Is your differentiation enough to support paid conversion?
4. Business model feasibility
- ☐ Are users willing to pay? How much? (must be tested in reality)
- ☐ What is rough customer acquisition cost?
- ☐ Can user lifetime value (LTV) cover customer acquisition cost (CAC)?
- ☐ Are there additional monetization paths? (ads, value-added services, B2B, etc.)
5. Rapid validation plan
- ☐ Can you build a testable prototype with minimum cost in 1-2 weeks?
- ☐ Can you find 10 target users for interviews?
- ☐ Can you design an experiment to validate the core hypothesis?
- ☐ Can you ask users to prepay deposits to validate willingness to pay?
Do not ask "Will you use this product?"
This question mostly gives false positives.
Ask instead:
- "How do you currently solve this problem?" (understand real behavior)
- "How many times did this problem bother you in the last week?" (understand frequency)
- "If there is a solution, but it requires changing your current habit, are you willing?" (understand change cost)
- "If it costs XX RMB, will you buy?" (understand willingness to pay)
Best validation: ask users to prepay deposits. Many people say they are willing to pay, but those who actually pay are your real target users.
Key metrics:
- Deposit-paying user ratio > 10%: demand is real and worth investment
- Deposit-paying ratio 5%-10%: demand exists but needs refinement
- Deposit-paying ratio < 5%: demand is invalid, or product concept has issues
Chapter Summary
In this chapter, through Xiao Ming's story, we learned how to evaluate product ideas from a product-manager perspective - the core is always: will users pay for this?
Core points
1. Three standards of real demand:
- Users are willing to pay for it (the most important standard)
- Users are willing to change behavior for it
- If no solution exists, users suffer clear loss
2. Path from ordinary idea to product people will pay for:
- Horizontal segmentation: find a specific user group, and the more segmented, the stronger willingness to pay
- Vertical deep dive: understand complete scenarios, solving emotions rather than only functions
- Value reconstruction: evolve from tools into solutions and build reasons to pay
3. Avoid fake-demand traps:
- Solving pseudo pain points (itch points instead of pain points)
- Market size is too small to support a business model
- Solution is more complex than the problem itself
4. How to validate willingness to pay:
- Interview 10 target users in depth
- Ask users to prepay deposits to verify true willingness
- Only when deposit-paying ratio > 10% is it worth investing
5. Refine product concepts with AI dialogue:
- Iterate through multiple rounds
- Focus on execution and action plans
- Set validation metrics and adjust direction promptly
Remember: good product managers do not create demand from thin air. They discover real needs that are ignored, underestimated, or poorly satisfied, then find ways to make users willing to pay.
In the next chapter, we will bring validated ideas and start learning how to use AI IDE to turn them into interactive product prototypes.