AI Lab

GTO Poker

A native macOS app for drilling solver-based preflop poker ranges.

Tools
Claude Code, Figma, spreadsheets
Time
1 week
Status
Personal tool, runs locally
Guardrails
All range data from me as JSON, plus a design system, CLAUDE.md file and an overall project plan
Illustration of a playing card, the ace of spadesPhotograph of two aces of spadesPixel-art icon of two playing cards

Context

I wanted solver-grade poker training for my own use that wasn’t locked behind a paywall.

What I delegated, and the calls I made

Marked rows are key decisions.

  1. Writing the code

    Claude Code wrote it from my plan and mocks

    Mostly AI

  2. Sourcing the range data

    All of it came from me

    All me

  3. Cleaning the data

    Claude helped clean it up

    Shared

  4. App design

    My Figma mocks guided the build

    Mostly me

  5. Table positions Override

    Claude wanted 6 seats; I required up to 9

    All me

    Tradeoff:
    more ranges to source and more layouts to design.
    Why:
    training should mirror the games I actually play.
  6. Scope Decision

    Preflop only for v1

    All me

    Tradeoff:
    the trainer covers just the start of a hand.
    Why:
    postflop scenarios multiply the data far beyond what I wanted to take on for a first version.

Outcome

It runs fast and works well on my laptop. Next, I’d consider adding postflop training.

GTO Poker on a Mac: the lojack’s opening range as a 13 by 13 grid of hands, the ones to open in orange, beside a six-seat table