All posts
SafetyMay 10, 2026 5 min read

Why triage rules belong in code, not prompts

Burying safety logic in a system prompt is a liability. Here's how CareGuard makes every urgency decision auditable.

By CareGuard Team

Large language models are remarkable at understanding what a patient is describing. They are far less reliable at consistently acting on it the same way every time. That gap is exactly where patient safety lives — and it's why CareGuard keeps the triage decision out of the model entirely.

The problem with prompt-based safety

A prompt that says 'always escalate chest pain to emergency care' works most of the time. But 'most of the time' is not a standard you can defend to a clinical governance board. Prompts can be overridden by clever phrasing, drift across model versions, and leave no record of why a decision was made.

What CareGuard does instead

The model has exactly one job in triage: extract the patient's symptoms faithfully, using their own words. Everything after that is deterministic code.

  • An explicit red-flag list scans the extracted symptoms.
  • On a match, urgency is forced to EMERGENCY — the model cannot override it.
  • When the picture is ambiguous, scoring escalates up, never down.
  • Every decision, and which red flags fired, is logged for audit.
The model proposes; the rules decide. That separation is the whole product.

The result is a triage layer you can actually reason about, test, and prove — not a black box you hope behaves.

See the guardrails in action

Deploy safe, guided intake and triage in a day. Keep clinical judgment with your team.

Hi! I can help you book an appointment and take down your details. To start — what kind of visit do you need, and roughly when works for you?