Build With AI

Build The
Smart Money App

An app that tracks where the most informed money is moving: Polymarket odds, insider buys, and what Congress is trading, all in one dashboard. I described it to Emergent and it built the whole thing in under 15 minutes. Here's the exact prompt so you can build your own.

Try Emergent →

Where the most powerful people invest is public information, but it's buried in three different places. This app pulls all three into one dashboard you can check on your phone. This is not financial advice. It's a way to see the pattern: when the people with the most information keep moving the same direction, that tells you something.

It tracks three signals:

Signal 1

Polymarket

Live prediction-market odds. People bet real money on what's about to happen, so the odds often move before the news does.

Signal 2

Corporate Insiders

Executives buying their own company's stock, pulled straight from their public SEC Form 4 filings.

Signal 3

Congress

Every stock our representatives trade, disclosed publicly on a legal delay. The one that feels like it shouldn't even be legal.

The home screen is the Conviction Signal: a score for each stock that lights up when all three groups are leaning the same way at once.

The Prompt Build It In Emergent

Open Emergent, paste the prompt below, and let it build. No coding required. Here is the exact prompt:

Copy-paste this into Emergent

Build a complete, production-ready, mobile-first web app called "Smart Money" — a dashboard that tracks where the most-informed money is moving, all in one place. No login or signup; it opens straight to the dashboard. === THE BIG IDEA === Three groups tend to know more than the public about where markets are heading: prediction-market bettors, corporate insiders, and members of Congress. All of their activity is public, but it lives in three different places. This app pulls all three into one phone-friendly dashboard and scores how strongly they agree on each stock. === TECH STACK === - Frontend: React + Tailwind CSS. - Backend: FastAPI (Python) + MongoDB. - The backend fetches and caches data from public sources, then exposes clean JSON endpoints the frontend reads. Build it on a phone screen first, then scale up to desktop. === DESIGN SYSTEM === - Dark mode by default. Premium fintech feel: calm, trustworthy, lots of breathing room, flat (no heavy gradients). - Exactly ONE teal accent color, used sparingly for emphasis and the active tab. - Green for buys / bullish, red for sells / bearish. - A monospace font for ALL numbers (prices, percentages, scores, dates). - Rounded cards with soft shadows, generous padding, large tap targets. - Smooth skeleton loaders while data loads, clean empty states, and a small "last updated" timestamp. === GLOBAL LAYOUT === - A top header on every screen: the app name "Smart Money" on the left, and a circular manual "Refresh" button on the right that refetches data and shows a spinner while loading. - Bottom tab navigation with 5 tabs: Conviction (home), Polymarket, Insiders, Congress, Watchlist. The active tab uses the teal accent. - A persistent small footer line on every screen, always visible: "Public-filings data. Not financial advice. Congressional trades are disclosed on a legal delay." === THE DATA (use real public sources, no paid keys) === 1. Polymarket — live prediction-market odds. Use Polymarket's public API (no key required). Pull trending/active markets with their current YES/NO odds and recent movement. 2. Insiders — corporate insiders buying or selling their own company's stock. Use the SEC EDGAR public system for Form 4 filings (no key required). For each filing capture: ticker, company, insider name and role, buy or sell, share count, dollar value, and filing date. 3. Congress — stock trades disclosed by U.S. representatives and senators. Pull from a public congressional-trading data source. For each trade capture: representative name, ticker, buy or sell, amount range, transaction date, and disclosure date (these are disclosed on a legal delay of up to ~45 days). - Cache results in MongoDB so the app is fast and doesn't hammer the sources. Refresh on a schedule and when the user taps Refresh. - IMPORTANT: if any live source is temporarily unavailable, fall back to clearly-labeled realistic sample data for that feed (mark it "sample data" in the UI) so the whole app always works end to end and never shows a broken screen. === THE HERO FEATURE: THE CONVICTION SIGNAL === For every stock ticker in the data, compute a single "Conviction" score from 0 to 100 that represents how strongly the three groups are leaning the SAME direction. - For that ticker, take the recent signal from each source (Congress trades, insider trades, and where a related Polymarket market exists, the prediction-market lean) and convert each into a simple bullish / neutral / bearish lean. - The score is HIGHER when more of the three sources agree on the same direction and the activity is recent and larger in size, LOWER when they conflict or there is little activity. Briefly document the exact formula you use in code comments. - When all three sources lean the same direction on a ticker, mark it with a ⚡ "high conviction" badge. - Each ticker card shows: the ticker symbol, company name, the Conviction score (large, monospace), the direction (green up / red down), and small icons showing which of the three signals are firing. === WHAT EACH TAB SHOWS === - Conviction (home): the headline screen. A list of tickers ranked by Conviction score, highest first, with the ⚡ badge on the high-conviction ones. Tapping a ticker opens a detail view that explains WHY: it shows the underlying Congress trades, insider trades, and any Polymarket market for that ticker, so the user can see exactly what's driving the score. - Polymarket: a list of trending prediction markets with their current odds and recent movement. Tap for detail. - Insiders: recent insider transactions from Form 4, newest first; each card shows company, insider name and role, buy/sell (green/red), dollar value, and date. Include a filter for "buys only." - Congress: recent congressional trades, newest first; each card shows the representative, ticker, buy/sell, amount range, transaction date, and disclosure date. - Watchlist: let the user save tickers (a star/add button on any ticker) and see only those, with their Conviction scores. Persist the watchlist (localStorage is fine). === POLISH === - Make it genuinely feel like a shipped product: fast, responsive, with thoughtful empty and loading states and a cohesive look across all five tabs. - It must look and feel great on a phone first. Build the entire app end to end, wire up all three data feeds, implement the Conviction score and the ⚡ badge, and deploy it.
Open Emergent →
3 Steps How To Use It

Step 1

Open Emergent

Head to Emergent and start a new build. You describe what you want in plain English, and its AI agents handle the coding, design, and hosting for you.

Step 2

Paste The Prompt

Copy the prompt above, paste it in, and hit go. Want it to track different things or look different? Just tweak the prompt before you send it. It's yours to change.

Step 3

Let It Build

Give it a few minutes to build the whole thing, then open it on your phone. Mine went from prompt to working dashboard in under 15 minutes.

One important note

This is not financial advice, and the app isn't about copying a trade the second it happens. It's about learning the pattern. Everything it pulls is public information, and congressional trades especially are disclosed on a legal delay, so treat it as a research tool, not a crystal ball.

The Only AI Masterclass You Need

Build AI Systems That Run Your Work, Business, And Life

If this guide helped, but you’re looking to go deeper, I got you!! My 30-Day Challenge takes you from saving AI tips you never use to actually building with AI, step-by-step.

I show you exactly how I automated two e-commerce brands, my social media, and most of my personal life, then hand you the agents, workflows & systems to do the same. I’m teaching you every single thing I know with one lesson and one build a day.

Join the AI Masterclass →

© 2026 Mariah Brunner. All rights reserved.