Before
They had a concept for civic transparency but were building outside their prior technical expertise. Ideas like relational database logic, JSON formatting and API integration were new ground. The question was simple. Turning it into a working system was not.
“What did a candidate say, and what did they do?”
In their own words
The turning point
In the AI Mastery program, they began using ChatGPT as a structured development tutor rather than a shortcut. It walked them through Airtable schema design, backend-to-frontend mapping and troubleshooting, step by step. They learned to get the structure right first and let automation come later.
“Applied AI becomes most powerful when used as a structured development partner.”
In their own words
After
They now have a functioning prototype in Lovable, backed by a relational Airtable schema that can hold local, state and federal candidate records. A search for the test profile "Jane" brings up a clean, neutral profile with a visible Consistency Score. They are already exploring n8n for the next phase of automation and live data syncing.
What it lets people do
Voters can look up a candidate and see campaign statements next to their historical voting behavior, presented without spin. The Consistency Score gives a quick, structured way to compare words and actions, and the design leaves room for people to later match candidates against their own values.
What they learned
They came away convinced that AI is most powerful as a structured partner, not a magic button. Building something people can trust starts with careful schema design and discipline about neutrality, with automation following only once the structure is clear.
“Iterative experimentation is critical when building outside prior technical expertise.”
In their own words
Said & Done: AI-Supported Civic Consistency & Transparency Platform was built during AI Mastery.
Read the full submission
Applied AI Excellence Award
Said & Done: AI-Supported Civic Consistency & Transparency Platform
Achievements
• Designed and developed a working civic transparency prototype using Lovable and Airtable.
• Built a structured candidate lookup interface demonstrating real-time profile retrieval (dummy data implementation).
• Designed a relational Airtable backend schema capable of supporting local, state, and federal candidate records.
• Created a structured “Consistency Score” framework comparing stated campaign positions with historical voting behavior.
• Applied AI as a structured learning and build partner to accelerate schema design and data modeling.
• Developed foundational architecture for future automation, live data syncing, and voter alignment modeling.
Tools
• Lovable (front-end prototype development)
• Airtable (relational backend database design)
• ChatGPT (architecture guidance, JSON logic tutoring, schema modeling, step-by-step development support)
• Structured dummy datasets for proof-of-concept testing
Methodology
Set & Done was designed as an applied civic technology prototype focused on clarity and neutrality.
The design objective was to create a simple, scalable system that answers a direct question:
What did a candidate say, and what did they do?
The build followed a layered implementation process:
1. Data Modeling & Schema Design
Airtable was used to create a structured backend capable of supporting:
• Candidate records
• Office level (local, state, federal)
• Terms served
• Campaign statements
• Historical voting behavior
• Issue-linked vote tracking
The backend was intentionally designed for future scalability and automation.
2. Front-End Prototype (Lovable)
A functional prototype was built in Lovable to:
• Allow searchable candidate lookup
• Display structured profile data
• Present a visible “Consistency Score”
• Demonstrate the concept with dummy test records (search example: “Jane”)
The front-end was designed to remain clean, neutral, and non-interpretive.
3. AI-Assisted Development
AI (ChatGPT) was used as a structured development tutor to support:
• Airtable schema design
• Understanding relational database logic
• JSON formatting principles
• API and integration concepts
• Backend-to-frontend mapping
• Troubleshooting structural issues
This project represents direct application of AI Mastery learning into real system construction.
4. Future Automation Roadmap
While the prototype is functional, the next phase includes:
• Automated population of candidate and vote data
• Backend syncing between Airtable and front-end
• Workflow automation (n8n exploration in progress)
• User-defined value alignment modeling
The foundation architecture has been established to support these future layers.
Learnings
• Applied AI becomes most powerful when used as a structured development partner.
• Building civic infrastructure requires careful schema design before automation.
• Neutral presentation demands architectural discipline.
• Relational database thinking is foundational to transparency systems.
• Automation should follow structural clarity, not precede it.
• Iterative experimentation is critical when building outside prior technical expertise.
This project moved from concept to functioning prototype through structured AI-assisted development.
It represents applied learning, architectural thinking, and civic impact experimentation.
Relevant URLs
• Lovable Prototype (View Only – Search “Jane” to test example profile)
• Airtable Backend Schema (View Only)
• Project Walkthrough Video (View Only – Demonstrating architecture and logic)
Written 15 February 2026· Submitted by the storyteller
Every story is written by a Mindvalley student or by someone our teachers have worked with. How we collect and check stories
