Advanced Squad Leader (ASL) Rules Assistant

An experiment: Can an AI model accurately and cost-effectively answer rules questions for a tabletop wargame with a 1M+ token rulebook? Built on OpenAI's Responses API.

Try the Demo View Eval Results How It's Built

The Domain Challenge

Advanced Squad Leader (ASL) is a tactical WWII board game that historically was played on cardboard maps with cardboard counters and dice.

Now most play happens digitally via VASSAL, but the platform only handles moving counters and rolling dice — all rules interpretation and calculation is still done entirely by the players.

A rules assistant is useful because the game and its rules are complex. During a game, players frequently refer to the 716-page rule book and tables for two purposes:

  1. Rule lookup: answer a question about the rules that doesn't require a calculation (e.g., "What is the movement cost to enter a woods hex?")
  2. Outcome calculation: given the game state, determine the dice roll (DR) needed to achieve an effect (e.g., "What DR do I need to break that squad given this terrain and fire modifier?")

This assistant is designed to cost-effectively support both use cases.

How It Works

1
Retrieve & Generate

OpenAI's Responses API uses a file_search tool over a vector store of the ASL rulebook; the model answers from the retrieved chunks and streams back, citing rule sections (e.g. A4.34).

2
Validate (optional)

Each citation is a clickable link that opens the rulebook PDF at the exact page, so you can check the answer against the source.

3
Evaluate

An LLM judge scores the answer against an expected answer, with pass / fail / needs-review verdicts tracked by model and question type.

4
Curate

Promising Q&A pairs are triaged into eval sets or SFT training data, feeding the loop that measures and improves the model.

Demo

Live demo showing a rules question, RAG retrieval, and cited response with PDF navigation.

Advanced Squad Leader is a trademark of Avalon Hill Games, Inc. This is a personal, non-commercial project with no affiliation with Hasbro, Avalon Hill, or Multi-Man Publishing.