Anterior open sourced a research preview of its symbolic reasoning library and an MCP server under the Apache 2.0 license. The library writes a health plan policy as a graph of narrow criteria; a deterministic solver walks the graph, asks an LLM agent, a database or a human reviewer one criterion at a time, and returns approve, escalate to human review or deny with a full reasoning trace. Anterior says it uses the approach across thousands of policies for prior authorization, HEDIS, claims and payment integrity.
Our readPlans weighing AI for medical necessity review can now inspect how the policy logic stays outside the model, which is what lets the same facts produce the same decision. It is an early preview, so it documents the method rather than any one customer's setup.