Trading interfaces are dense and intimidating, and the gap between 'seeing your positions' and 'acting on them' usually means menus, forms, and manual order entry.
← Back to portfolio// project showcase
AI Trading Workstation
FinAlly
A Bloomberg-style trading workstation that streams live prices and lets an LLM assistant analyse holdings and execute trades from natural-language instructions. Built as a course capstone, entirely via agentic coding workflows.
// the story
Problem, approach, result
Built a Bloomberg-style workstation that streams live prices over SSE, visualises a portfolio as a heatmap and P&L chart, and adds an LLM assistant that analyses holdings and executes trades from natural-language instructions — Next.js + FastAPI in a single Docker container, with structured-output LLM calls driving the trade logic.
Demonstrates end-to-end agentic product delivery — real-time data streaming, a stateful simulated portfolio, and an LLM wired safely into actions rather than just chat. Built entirely via coding agents as a course capstone.
// tech & skills
Built with
- Next.js
- TypeScript
- Tailwind
- FastAPI
- SQLite
- SSE streaming
- LiteLLM / OpenRouter
- Docker
- Structured-output LLM calls