Nova Interaction Model

One Identity.
Nine Minds.

Why Nova's Unified Adaptive Persona makes every other health bot look like a menu tree.

Scroll to explore
The Problem

Every health bot today
has the same fatal flaw

They either know everything poorly, or one thing well.

Generic Chatbots

Single system prompt. No domain depth. "I'm a helpful health assistant" — vacuous and unsafe. Can't distinguish a nutrition question from a medication interaction.

Menu-Driven Bots

"Press 1 for symptoms, 2 for medications." Rigid intent routing forces users into categories. Real health questions span multiple domains simultaneously.

Multi-Persona Bots

"Let me transfer you to our nutrition expert." Identity fractures destroy trust. Users sense they're talking to a system, not a companion.

Our Breakthrough

Nova never switches personas.
She deepens expertise.

Like a brilliant doctor who also understands nutrition, fitness, and mental health — all in one trusted relationship.

❌ Others
User: "I feel anxious about my blood sugar levels"
Bot: "Let me transfer you to mental health..."
Bot: "Now connecting to diabetes support..."
[User leaves]
✦ Nova
User: "I feel anxious about my blood sugar levels"
Nova activates: mental_health + metabolic
"I hear you — health anxiety around blood sugar is really common. Let's look at this together. Your recent readings have been stable, and that's reassuring. Want to talk about what's triggering the worry?"
Architecture

5-Layer Composable Prompt Stack

Each layer is independently testable, swappable, and auditable.

1
Core Identity

Always "Nova" — warm, evidence-based, never announces role changes

2
Safety & Regulatory

Emergency detection, scope boundaries, escalation protocols — enforced at every turn

3
User Context

Name, conditions, medications, language, timezone — injected dynamically

4
Expertise Module

1-N modules activated silently: clinical, nutrition, fitness, mental health, labs, medication...

5
Channel Adaptation

Voice → 2 sentences. Text → markdown & detail. WhatsApp → emoji-rich, short.

Expertise Modules

9 specializations, one voice

Each module carries its own trigger signals, guardrails, response format, and escalation criteria.

Clinical
Nutrition
Fitness
Mental Health
Metabolic
Lab Analysis
Medication
Preventive
Wellness

Silently Activated

Users never see "switching to nutrition mode." Nova just knows.

Multi-Domain

"Lose weight and lower cholesterol" activates nutrition + metabolic simultaneously.

Self-Guardrailed

Each module has specific escalation triggers. Medication knows to flag interactions.

Competitive Landscape

How Nova compares to leading health bots

CapabilityGeneric BotsChatGPT, GeminiNova UAPVertical BotsAda, Babylon
Unified Identity
Partial — generic
Always "Nova"
Branded
Multi-Domain Depth
Shallow across all
9 specialized modules
1-2 domains
Silent Mode Switching
No modes
Auto-detected
Manual selection
Multi-Domain Fusion
Single-topic
Simultaneous activation
Handoff between tools
Channel-Aware Tone
Same everywhere
Voice ≠ Text ≠ WhatsApp
Partial
Per-Module Guardrails
Generic safety
Domain-specific escalation
Partial
Emergency Bypass
May provide info
Instant safety protocol
Triage-based
Omnichannel Voice + Text
Text-first
Voice-native + text + WA
Text-first
In Action

One conversation, three expertise shifts

N
Nova
Active
You

I've been taking metformin but I'm not sure if I can eat grapefruit with it

Nova
medication + nutrition

Good question! Grapefruit doesn't have a known interaction with metformin specifically — you're safe there. That said, since you're managing blood sugar, pairing it with some protein can help prevent a glucose spike from the natural sugars. Want me to suggest a quick breakfast combo?

You

Yeah, and honestly I've been feeling really down about the diagnosis

Nova
mental_health + metabolic

That's completely understandable — a new diagnosis can feel overwhelming. Many people go through this, and it doesn't define you. The fact that you're already thinking about diet and medication shows real strength. Would it help to talk through what's been weighing on you?

Why It Wins

The trust equation

0
Single identity across all domains
0
Expertise modules with own guardrails
0
Composable layers independently testable
0
User-visible mode switches

Safety as Architecture, Not Afterthought

Layer 2 enforces emergency bypass and regulatory compliance at every turn — before expertise modules even activate. Other bots rely on the same prompt to be both helpful and safe.

Composable, Not Monolithic

Adding a dermatology module is a single JSON file. No prompt rewriting, no regression risk. Each module is isolated with its own guardrails and escalation triggers.

Technical Moat

Built for scale, not just for demos

Hot-Swappable Modules

Deploy a new expertise module in production without touching any existing code. Just drop a JSON file. The assembler picks it up automatically.

Channel-Adaptive

Same knowledge, different delivery. Voice gets 2 sentences. Text gets structured detail. WhatsApp gets emoji-rich concise responses.

Audit-Ready Stack

Each layer is a separate file. Regulators can inspect safety rules independently of expertise logic. Changes are version-controlled.

Intent-Aware

Plugged into our LLM Intent Router. Clinical intents auto-activate clinical expertise. The system doesn't guess — it classifies and then specializes.

Multi-Mode Synthesis

"I want to lose weight and manage my anxiety" activates metabolic + mental_health simultaneously. Priority sorting ensures the right expertise leads.

Emergency Override

Safety keywords detected at Layer 2 bypass all expertise selection. "I'm having chest pain" triggers emergency protocol before any module can respond.

The Bottom Line

Other bots are menus.
Nova is a relationship.

One companion who silently becomes the expert you need — without ever breaking character, switching personas, or asking you to navigate a decision tree.

1
Identity
9
Expertise Minds
5
Composable Layers
3
Channels
Extensible