I’m not just building a poker UI. I’m building a system that can understand the table.

This project started with a simple idea:

Can software look at a poker table and turn what it sees into structured game logic?

The deeper I get into it, the more interesting the engineering becomes.

The system has to deal with things like:

→ Card recognition — identifying cards from the screen → Board detection — understanding the current board state → Player positioning — determining where players are located → Action recognition — interpreting Fold, Call, and Raise → OCR — extracting information from visual elements → Coordinate mapping — knowing where important elements exist on different layouts → Game-state logic — turning all that visual information into something the application can actually understand

And this is where AI-assisted development becomes powerful.

I can use an AI coding agent to help investigate the codebase, implement changes, run tests, and work through bugs.

But the outcome still depends on how I design the logic, test the edge cases, and verify what the system is actually seeing.

The goal isn't:

“Make AI write a poker application.”

The goal is:

“Build a system that can reliably understand what is happening on the table.”

That's a completely different engineering problem.

Right now I'm focused on making the recognition and game-state pipeline more reliable because one incorrect card, coordinate, or player action can affect everything that comes after it.

Computer vision + AI + software engineering = some seriously interesting problems. 🧠🔥

What would you build with this kind of technology if you had reliable real-time visual recognition?