Engineering Notes

Notes on web and ML engineering from Greenskin Labs, including the Rules Oracle RAG series.

Series

Engineering the Rules Oracle

Modern tabletop games rely on fragmented rulebooks, supplements, and changing FAQs. The Rules Oracle is a hosted Q&A engine built to return cited, page-referenced answers to complex rules questions. This series covers the engineering behind it.

Access is currently invite only during the beta period.

Part 1

In Good Character: Designing an Ingestion Pipeline for Hostile Tabletop Rules

Tabletop rulebooks are hostile to naive RAG: scanned PDFs, custom symbols, dense tables, and no reliable text layer. I used that mix as a validation corpus and built ingest for Structural Truth—heading paths, icon meanings in text, and book page numbers—by pivoting from unpdf and Document AI to Claude Haiku vision parse. Per-page and book-level caching makes re-chunking cheap; citation integrity belongs at the front of the pipeline.

  • RAG
  • TypeScript
  • Vision Parse
  • Claude
  • Data Engineering

Part 2

Pulling Rank: Using Fused Retrieval to Bridge the Alias Gap

Standard vector search has a vocabulary problem. It finds things that sound like your question. But when rules are written for a parent category and the question names a specific type, similarity is not enough. This second article in my series on the Rules Oracle details three parallel search lanes and the ingest-time supersession flag I use to bridge the Alias Gap. Finding the right rule is a matter of lanes and lexical safety nets, not just semantic proximity.

  • RAG
  • TypeScript
  • Hybrid Retrieval
  • pgvector
  • RRF
  • Data Modeling