Using AI to Build an AI App - Part III
Being able to build software is a power.
As the world digitizes and AI powers-up, being able to develop and deploy software rises from power to super power.
You can create apps, small tools to make your life easier, entire software suites… and then you can:
sell them
use them in your daily grind
license them for recurring revenue
bolt them into your existing businesses
share them to improve your tools (and your skills) at faster rates
For instance, I wanted a way to use AI to help me track my goals, habits & tasks… and make sure I was staying on track. That’s why I built Orion, the AI Life Copilot.
This series is focused on how to use AI and other cutting-edge tools to build software. We should all have this superpower. I started this series using a tool from Google called Project IDX.
I am an early alpha tester for Google, and have collaborated with them on the development of several features of Gemini, their AI system. My work focused on integrating Gemini into Workspace so businesses can leverage AI as a true co-worker.
Project IDX has launched since Part I and Part II of this series, then Project IDX merged into Firebase Studio, another Google experience. The combined artifact is very powerful but also quite complicated. It's going to elevate already strong app builders into artists.
But that's not me.
I’m a business strategist, data engineer and investor not a hardcore software engineer, so Project IDX / Firebase Studio became too technical and time consuming for me.
Vibe Coding
So I switched to Lovable.
Lovable turns ideas into applications in seconds.
You chat your concept into a working MVP, connect it with a backend and you can publish all in the same 15-minute window. Talk about accelerating development loops.
Lovable have since added the ability to select individual elements, or decide to Chat-only and not risk making any codebase commits. They recently enabled multiplayer…aka letting teams of people build together on the same canvas and codebase.
Start by explaining two things:
the function of the app - what it does
the form of the app - how it looks, the users experience
Then link to supabase as your backend.
Then I STRONGLY SUGGEST you build authentication (sign in, sign up pages) and the protected routes through the app. I've made the mistake of building the app out and then trying to put the front door and the hallways in afterwards, that's not the right way to do it.
Get the foundation features working before adding new ideas… and always run through ALL your features every time you make a change that touches your database, control flows, anything that makes your app work. You'd be surprised how often vibe coding leads to vibe debugging.
Best part about screwing up in Lovable: you have a time machine. You can revert to earlier working versions. Caution here: changes made to your databases are not automatically rolled back by these reverts (as of this writing, I bet they are working with supabase on a joint schema to allow for this) so be extra careful when the AI suggests SQL changes. Those impact your backend and there's no easy way to rollback those changes.
Now that I have a working AI Life Copilot with users, I want to incentivize conversion to from free-to-paid. So I asked the AI in chat mode:
“I want to incentivize conversion to the paid version of this app. Can you review the code and think about paywalls I can put up and other ways I can drive users to paying for the paid version?”
The system scanned my code and came back to me in about 25-seconds with the following plan:
See how I'm using it to generate strategies not just generate lines of code?
From the AI:
After reviewing your codebase, I can see you have a good foundation for a freemium model with some premium features already implemented, including AI advice, weekly planning, and premium AI models. However, there are several opportunities to enhance monetization by implementing strategic paywalls and improving the value proposition of your premium tier.
Premium Feature Implementation Strategy
1. Enhance Existing Premium Features
Weekly Planning: Already paywalled but could be enhanced
AI Advice & Council: Currently limited for free users
Premium AI Model Access: Already differentiated
2. New Strategic Paywalls
Habit Tracking Limits: Cap daily/weekly/monthly habits for free users
Advanced Analytics: Restrict detailed insights and data exports
Goal Setting Caps: Limit number of goals for free users
Journal Entry Limits: Cap entries or restrict templates
3. Premium User Experience Improvements
Remove Usage Limits: Highlight unlimited AI interactions
Priority Support: Add dedicated support for premium users
Premium UI Elements: Visual differentiators for paid users
Profile Badges & Achievements: Exclusive premium achievements
4. Conversion-Focused UI/UX Changes
Feature Discovery Tours: Guide users to premium features
Strategic Upgrade Prompts: Show upgrade CTAs at usage limits
Premium Preview Mode: Time-limited trials of premium features
Social Proof Elements: Testimonials from premium users
Detailed Recommendations
1. Strategic Feature Limitations & Paywalls
Habit Tracking Limits:
Cap free users at 3 daily habits, 1 weekly habit, and 1 monthly habit
Limit habit history/analytics to 30 days for free users
Offer exclusive habit templates and advanced streak tracking for premium users
Analytics & Dashboard Features:
Offer basic analytics to all users, but reserve detailed insights and trend analysis for premium
Limit data history to 30 days for free users, unlimited for premium
Create premium-only dashboard visualizations showing correlations between habits and journal entries
Journal Entry Caps:
Limit free users to 3-5 journal entries per week
Reserve guided journal templates and emotion tracking for premium
Implement AI-powered journal insights as a premium-only feature
Council/AI Advisor Interactions:
Maintain your existing daily limits (I see 5 for free, 20 for premium)
Reserve certain advisors (like Rockefeller for business) for premium users only
Provide higher quality AI responses to premium users
2. User Experience Improvements for Premium Users
Visual Distinction:
Add premium badges and visual indicators throughout the app to highlight premium status
Create exclusive themes and UI customizations for premium users
Implement special animations or interactive elements only for premium accounts
Exclusive Features:
Develop premium-only exports and data portability features
Create "power user" tools like data import/export, API access, or integrations
Implement priority queuing for AI features during high-demand periods
Social & Community:
Create premium-only forums or mastermind groups
Implement sharing features that highlight premium status
Develop premium-exclusive challenges and leaderboards
3. Conversion Optimization Strategies
Strategic CTA Placement:
Show upgrade prompts when users hit usage limits
Place "Premium Preview" buttons next to locked features
Show premium benefits when users engage with limited features
Conversion-Focused Onboarding:
Create a separate onboarding flow highlighting premium benefits
Implement a feature discovery tour pointing out premium capabilities
Showcase premium features during core user journeys with subtle "locked" indicators
Value Demonstration:
Add comparison tables showing free vs premium features
Implement "premium for a day" free trials
Create case studies showcasing how premium users achieve more
Limited-Time Offers:
Implement seasonal discounts or special promotions
Create founder or early adopter rates to drive initial conversions
Consider lifetime deals for early premium adopters
These are novel ideas across different dimensions that should help me create a clear pitch for premium.
Better yet, it even suggested an implementation schedule based on impact:
Implementation Priorities
First Wave (Highest Impact/Lowest Effort):
Implement basic usage limits on existing features (habits, journals, AI interactions)
Add upgrade CTAs at strategic points in the user journey
Create free vs premium feature comparison page
Second Wave (Premium Experience):
Develop premium-exclusive analytics and insights
Implement premium visual indicators and UI enhancements
Create exclusive templates and power tools
Third Wave (Retention & LTV):
Implement premium-exclusive challenges and social features
Develop advanced data export and integration capabilities
Create tiered premium plans for higher value segments
This strategy balances creating meaningful value for premium users while maintaining a useful free tier that can attract and convert new users.
Not only did I get interesting ideas I hadn’t considered ever, such as premium user for a day lotteries to give people a taste… Genius. Maybe gamify it with a spinning wheel? Gamification is a driving force for building, engaging and monetizing on the internet - read this deep dive for more detail on implementation:
Try Lovable today to see what tools you can summon into existence.
You can see, it not only gave me good suggestions but it layered together an implementation plan. This is the quality of collaboration we are already enjoying from building software with AI. Can you imagine how powerful AI tools will become in just another 12-months? We will be building true masterpieces that were previously only achievable by the top 200 or 300 programmers on the planet.
We are all builders and technologists now.
Friends: in addition to the 17% discount for becoming annual paid members, we are excited to announce an additional 10% discount when paying with Bitcoin. Reach out to me, these discounts stack on top of each other!
Thank you for helping us grow Life in the Singularity by sharing.
I started this letter in May 2023 to track all the accelerating changes in AI.
Our brilliant audience includes engineers and executives, incredible technologists, Fortune 500 board members and thousands of people who want to use technology to maximize the utility in their lives.
To help us continue our growth, would you please Like, Comment and Share this?