MidCap Alpha

UK mid-cap equity intelligence system with real market data and an interactive trading academy.

What It Does

Intel Mode — Enter a natural language query about a UK stock. Three specialist desks analyse it in parallel (Research, Execution, Corporate Events), then a CIO desk synthesises everything into a single recommendation. Real market data from Yahoo Finance is injected automatically.

Academy Mode — Browse 30 equities trading concepts across 5 categories, all contextualised for UK mid-cap markets and LSE structure.

Quick Start

npm install

Create .env in the project root:

VITE_ANTHROPIC_API_KEY=sk-ant-your-key-here

npm run dev

Open http://localhost:5173

Architecture

Query → [Research Desk | Execution Desk | Events Desk] → CIO Synthesis → Recommendation
                         ↑                                                    ↓
                  Real market data                                    📚 Learning Layer
                  (20 UK stocks)

Desk Structure

Desk	Role	Colour
Research Analyst	Investment thesis, key metrics, conviction score	Blue
Execution Strategist	Liquidity profile, execution strategy, market impact	Green
Corporate Events Monitor	RNS events, catalysts, corporate action risk	Amber
CIO Synthesis	Final recommendation combining all three views	Gold

Market Data

Pre-fetched Yahoo Finance data for 20 UK-listed stocks including Bytes Technology, Dunelm, Auto Trader, Halma, QinetiQ, Dr. Martens, and more. Covers price, P/E, EV/EBITDA, FCF, volume, dividend yield, beta, and analyst consensus.

Tech Stack

• React 18 + TypeScript + Tailwind CSS v3
• Vite
• Anthropic Claude API (claude-sonnet-4-20250514)
• Yahoo Finance (pre-fetched static data)

Commands

npm run dev       # Dev server
npm run build     # Production build
npx tsc --noEmit  # Type check