The Argument Factory
Evidence-grounded AI system
The Argument Factory
RSRAG began as a joke about making thinkers fight. The interesting problem arrived almost immediately: a language model can argue both sides of nearly anything, but that does not mean either side has a meaningful position in the written record. The project became an experiment in inspectability. It gathers candidate works through controlled source adapters, routes uncertain editorial decisions through a private review studio, publishes immutable corpus versions, and keeps every generated claim connected to the passage that supports it.
Role
- Designed the product model, editorial workflow, evidence lineage, and public presentation system.
- Built a human-reviewed corpus pipeline with rights checks, immutable publication snapshots, and bounded model-assisted analysis.
- Separated two retrieval and advocacy lanes so each position is constructed and validated against its own published corpus.
- Developed the project through a Socratic collaboration with AI: propose, interrogate, test, inspect failure, and revise.