AI my Stock Portfolio

My stock portfolio is spread across multiple brokers in different countries — Japanese stocks with one broker, European positions with another, investment funds in a third account. Each has its own dashboard, export format, and way of presenting performance. Relying on these dashboards as my single source of truth felt uncomfortable. What if a broker changes its interface or suspends my account? How do I compare positions across currencies, time horizons, and purchase dates?

I wanted local, inspectable, portable data ownership — files on my own disk that don’t disappear if a broker changes policy. Not just the raw transaction records, but the analysis process itself.

This post tells the story of how I built a suite of tools to solve that problem. But the real journey wasn’t about writing Python scripts — it was about discovering how to think about stock performance in the first place. This was also a trial run in using AI end-to-end: Gemini for strategic thinking and high-level concepts, Claude and VS Code Copilot for implementation and debugging.