Before
They had watched how voters learn about candidates change. Newspapers and long-form reporting gave way to flyers handed out on voting lines and scattered social media posts. The idea for a better tool had been with them for years, but building it meant stepping well outside what they knew technically.
“Voters deserve accessible, real-time clarity about who they are voting for — especially while standing in line.”
In their own words
The turning point
In AI Mastery, they began using ChatGPT as a structured learning partner. Step by step, it guided them through Airtable schema design, data structuring, JSON concepts and how a front end connects to a backend. That support made it possible to apply what they were learning directly to civic technology.
“AI can accelerate applied learning when building outside one’s prior technical expertise.”
In their own words
After
They built a working Lovable prototype with searchable dummy data and a structured Consistency Score model, backed by an Airtable schema that covers local, state and federal candidates. The core principle stays simple: remove interpretation, show consistency. Live data and automation are in development, and the foundation is in place.
What it lets people do
Voters can look up a candidate and see their profile, campaign statements and voting history in one place. The platform shows plainly where words and votes align or diverge, without political spin. A planned layer will let people enter their own values and compare them with each candidate.
What they learned
They found that trust grows when information is shown without interpretation, and that neutrality takes deliberate structural restraint. They also learned that AI can speed up learning when you build beyond your expertise, and that automation should follow clarity, not precede it.
“Set & Done began as an idea that had been on my heart for years — driven by a belief that voters deserve better tools to make informed decisions.”
In their own words
Said & Done: Civic Consistency & Transparency Platform was built during AI Mastery.
Read the full submission
Impact Project of the Year
Said & Done: Civic Consistency & Transparency Platform
Achievements
• Designed and developed a civic transparency prototype enabling voters to access candidate profiles, campaign statements, and historical voting behavior in one place.
• Built a working Lovable front-end prototype with searchable dummy data demonstrating candidate lookup and a structured “Consistency Score” model.
• Designed and structured an Airtable backend schema to support local, state, and federal candidate data.
• Created a non-interpretive data framework focused strictly on “What was said” vs “What was done.”
• Established the foundation for a future voter-alignment layer allowing users to input their own values and compare alignment across candidates.
• Applied AI Mastery learning directly into civic technology experimentation and infrastructure design.
Tools
• Lovable (front-end prototype application)
• Airtable (backend database schema design and data modeling)
• ChatGPT (architecture guidance, schema tutoring, JSON logic understanding, step-by-step build support)
• Manual dummy data modeling for proof of concept
Methodology
Set & Done was born from a simple but increasingly urgent observation:
There was a time when voters could rely on newspapers and long-form reporting to understand candidates. Today, many people encounter information through flyers handed out on voting lines or fragmented social media content.
Voters deserve accessible, real-time clarity about who they are voting for — especially while standing in line.
The core principle of Set & Done is intentionally simple:
Remove interpretation.
Show consistency.
The platform architecture includes:
1. Candidate Profile Layer
• Office level (local, state, federal)
• Terms served
• Campaign statements
• Public positions
2. Voting Record Layer
• Historical voting behavior (where applicable)
• Structured vote records tied to specific issues
3. Consistency Model
• A non-interpretive comparison between stated campaign positions and recorded votes
• Structured scoring logic without political bias
• Clear presentation of where statements and actions align or diverge
4. Future Alignment Layer (Planned Phase)
• User-created value profiles
• A third comparison window allowing voters to see how their personal values align with each candidate
The current Lovable prototype is functional using dummy data (search example: “Jane”).
Airtable serves as the backend schema foundation. Automatic population of live candidate data and advanced automation workflows are in development.
AI (ChatGPT) functioned as a structured learning partner throughout the build process — guiding step-by-step application of:
• Airtable schema design
• Data structuring logic
• JSON formatting concepts
• Front-end and backend integration principles
While full automation and live data syncing are not yet implemented, the architecture foundation is established.
Learnings
• Civic trust increases when information is presented without interpretation.
• Neutral systems require deliberate structural restraint.
• Schema design is foundational to transparency and accountability tools.
• AI can accelerate applied learning when building outside one’s prior technical expertise.
• Automation should follow clarity — not precede it.
• Civic technology requires both technical discipline and ethical intentionality.
Set & Done began as an idea that had been on my heart for years — driven by a belief that voters deserve better tools to make informed decisions.
It is now an applied prototype and continues to evolve toward greater scale and automation.
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
