Skip to main content

​
Why Rubric?

Healthcare AI is high-stakes. A missed red flag or incorrect triage can have serious consequences. Rubric helps you continuously evaluate your voice AI’s clinical decision-making so you can ship with confidence.

Clinical Evaluation

Did the AI correctly identify symptoms? Was the triage level appropriate?

Safety & Compliance

Did the AI miss any red flags? Did it follow clinical protocols?

Human Review

Route flagged calls to clinicians for expert grading and feedback.

Track & Improve

Monitor metrics over time. Compare model versions. Catch regressions.

​
How It Works

1

Ingest

Send patient call recordings, transcripts, or DICOM studies via SDK
2

Evaluate

Automated clinical scoring: triage, safety, guidelines
3

Review

Clinicians grade flagged calls in purpose-built UI
4

Iterate

Track improvements across model versions

​
Quick Start

Log your first patient call in 5 minutes:
quickstart.py
from rubric import Rubric

client = Rubric(api_key="your-api-key")

# Log a patient triage call
client.calls.log(
    project="patient-triage",
    
    audio_url="https://storage.example.com/calls/call_123.wav",
    
    transcript=[
        {
            "speaker": "agent",
            "text": "How can I help you today?",
            "start": 0.0,
            "end": 2.1
        },
        {
            "speaker": "patient",
            "text": "I've been having chest pain since yesterday.",
            "start": 2.5,
            "end": 5.8
        }
    ],
    
    ai_decision={
        "triage_level": "urgent",
        "extracted_symptoms": ["chest_pain"],
        "routed_to": "cardiology"
    }
)

​
Use Cases

Use CaseWhat Rubric Evaluates
Patient TriageTriage accuracy, red flag detection, appropriate escalation
Symptom AssessmentSymptom extraction, follow-up questioning, differential coverage
Radiology AIFinding detection accuracy, report quality, critical finding alerts
Appointment SchedulingUrgency matching, specialist routing, availability optimization
Nurse HotlinesProtocol adherence, safety netting, empathy scoring
Mental Health SupportCrisis detection, appropriate referrals, tone assessment
Post-Discharge Follow-upRecovery assessment, complication detection, care plan adherence

​
Next Steps

Platform Capabilities

Explore all Rubric features

Quickstart Guide

Get up and running in 5 minutes

Try the Sandbox

Explore with pre-loaded healthcare data

API Reference

Full API documentation