Every answer passes through five safety gates.
Dana doesn't just generate text — it routes every patient question through a structured pipeline that classifies intent, selects a guideline-bound template, validates safety, and logs the outcome.
Classification
Each message is classified by intent (education, symptom, dosing, emergency) and risk level before any response is generated.
Template Selection
The right response template is selected from a curated, organization-tunable library — never improvised from scratch.
Guideline-Bound Generation
The response is generated within the boundaries of ADA 2025, AHA/ACC 2024, and GINA 2024 clinical guidelines.
Safety Validation
Two layers of validators check for dosing language, diagnostic claims, and emergency triggers — blocking unsafe outputs.
Audit Logging
Every classification, template, validation result, and final response is logged for organizational review.
Result: 100% governed
No raw LLM output ever reaches a patient. Every response is shaped, checked, and recorded.
Built on the standards your clinicians already follow.
ADA 2025
American Diabetes Association Standards of Care
AHA / ACC 2024
American Heart Association hypertension guidelines
GINA 2024
Global Initiative for Asthma management strategy