--- title: Zero-hallucination agentic RAG for clinical triage guidelines company: Schmitt-Thompson Clinical Content date: '2026-06-12' summary: >- Schmitt-Thompson Clinical Content (STCC), the source of nurse triage guidelines used by most North American medical call centers, partnered with Vstorm to build a four-stage agentic RAG system on Pydantic AI. By treating the triage decision trees as the only source of truth and tracing every step with Pydantic Logfire, the system reached 0% hallucinations across 329 clinician-validated scenarios. industries: - Healthcare productsUsed: - Pydantic AI - Pydantic Logfire canonical: 'https://pydantic.dev/case-studies/stcc' --- > Markdown version of [Zero-hallucination agentic RAG for clinical triage guidelines](https://pydantic.dev/case-studies/stcc) — the canonical HTML page. > > Schmitt-Thompson Clinical Content · 2026-06-12 · Healthcare > > "We approached this as a safety program first." — Matthew Thompson, Product Manager, STCC > > All case studies: [/case-studies.md](https://pydantic.dev/case-studies.md) · Site index: [/llms.txt](https://pydantic.dev/llms.txt) --- Learn how Pydantic AI powered a four-stage agentic RAG pipeline that answers strictly from STCC's triage decision trees, with Pydantic Logfire making every step traceable and auditable, and zero hallucinations across 329 clinician-validated scenarios. Read the full case study↗