Doug Fir Labs

Blog

Writing from Doug Fir Labs

Essays and release notes from Doug Fir Labs on neuro-symbolic AI, reasoning protocols, and the infrastructure that lets agents reason verifiably.

Glowing network of connections through douglas fir roots

Does the Evidence a Model Cites Drive Its Conclusion? Our preprint is out

A pre-registered causal test of declared evidence relations in Scholialang reasoning traces on Qwen2.5-7B-Instruct. A model's emitted symbolic label can causally steer its subsequent conclusion, even when the accompanying facts disagree.

Preprint3 min readRead
Reasoning protocol graph woven through douglas fir roots

Reasoning Needs a Protocol Layer

Scholialang helps agentic systems preserve reasoning state, use tools without quality loss, and reduce context cost across long-horizon work — a durable protocol for claims, evidence, decisions, contradictions, and verification across agents.

Product Release6 min readRead
Forest canopy aerial

Why Neuro-Symbolic Architecture Is the Missing Layer in LLM Infrastructure

Large language models are powerful pattern matchers, but pattern matching alone doesn't constitute reasoning. We explore how composing symbolic reasoning primitives with neural inference creates models that are more capable, auditable, and trustworthy.

Research7 min readRead