I
API ONLY
Server-to-server REST API
You build the UI (user interface) inside your own application. Authentication via OAuth or API key. Modules return structured JSON your app renders natively.
API
Automate the protocol your coaches deliver.
Your coaches are good at coaching. What slows them down is building a personalized plan for each member from that member's data — and doing it consistently across a roster. Clinical Reasoning interprets the data; the protocol builders generate the plan; your coaches do what they do best.
Practitioner-supervised. Rule-anchored. Evidence-cited. HIPAA (Health Insurance Portability and Accountability Act)-compliant, BAA (business associate agreement)-ready.
15+ hours
saved per practitioner per week on interpretation and plan assembly
6
protocol domains generated per member, not a single generic curriculum
Cited
evidence behind every recommendation a coach delivers
Coaching scales. Personalization is what doesn't.
A curriculum can be delivered to thousands. A plan built from one member's labs, session notes, health history and conditions has to be produced for each of them — which is where the model breaks.
TODAY
A curriculum, lightly tailored
1
Members get a program with some branching, and coaches adapt it in conversation. The adaptation depends on the individual coach’s knowledge, and it isn’t reproducible across a roster.
2
Making it genuinely personalized would mean a clinician interpreting each member’s data and building each plan — which the unit economics of a coaching platform don’t support.
WITH TERA MODULES
A generated plan per member
1
Clinical Reasoning interprets each member’s biomarkers, symptoms, and history, returning findings with citations rather than a coach’s recall.
2
The protocol builders generate a personalized plan across six domains. A practitioner approves it, and your coaches deliver it — the same quality bar for every member on the roster.
The shift
From adapting a curriculum to generating the plan for each member.
Member dataClinical reasoningPersonalized protocol
The modules this uses.
Clinical interpretation, personalized protocol generation, and a patient-facing surface that keeps the plan running between coaching sessions.
Module 02
Clinical Reasoning
Interprets biomarkers, symptoms, health history, and conditions into structured findings with citations — giving every coach the same clinical starting point.
Module 03
Nutrition Protocol Builder
Generates personalized nutrition plans from the member’s findings, goals, and health context — including foods, eliminations, and macronutrient targets.
Module 05
Fitness Protocol Builder
Builds individualized exercise protocols around the member’s goals, conditions, current capacity, and broader care plan.
Module 10
Tera Patient Copilot
Delivers the approved plan between coaching sessions, guiding the member daily and keeping execution connected to the practitioner and coach.
All nine modules are available — these are the ones this use case starts with.
How it works.
The practitioner stays in control. The modules interpret and assemble; your coaches focus on delivery, accountability, and the member relationship.
Step 01
Member data in
Labs, intake, symptoms, health history, and wearable data pass into Clinical Reasoning through the API or your existing integration.
Step 02
Findings returned
The rules engine interprets the member’s data and returns structured findings with citations — consistently across the entire roster.
Step 03
Plan generated
The protocol builders generate a personalized plan across the relevant domains based on those findings and the member’s goals.
Step 04
Practitioner signs, coach delivers
A practitioner reviews and approves the plan. Your coach then delivers it with the clinical groundwork already done.
Member dataClinical reasoningPersonalized protocolCoach delivery
Clinical safeguards
Safe AI you can embed.
Clinical defensibility is the precondition for embedding AI into any healthcare platform — three architectural pillars built to pass your compliance, legal, and clinical leadership reviews.
01Supervision
Practitioner-supervised by design
Tera AI generates; the licensed clinician approves. Every condition hypothesis, every protocol, every adjustment is reviewed and signed off before it reaches the patient.
02Reasoning
Reasoning is rule-anchored, not improvised
Tera does not ask a language model to interpret biomarkers. A proprietary clinical knowledge base maps results and wearable metrics to functional ranges deterministically, then to conditions and protocols. The model only summarizes what the rules produced.
03Evidence
Every recommendation is evidence-cited
Three knowledge bases — biomarker to condition, condition to protocol, food to condition and health goal — with every mapping backed by peer-reviewed citations. Audit-ready and inspectable.
Clinical AI architecture
Rules produce the findings. AI communicates them.
Practitioner supervised
Rule anchored
Evidence cited
Integration
Three ways to deploy.
Pick the integration depth that matches your engineering capacity and brand requirements. All three deliver the same clinical AI underneath.
II
EMBEDDED SDK
Drop-in React components
Your brand, your styling, our clinical logic. Embed the modules as React components in your existing application without building the interface from scratch.
SDK
III
WHITE-LABEL HOSTED
We host the interface; you brand it
Tera hosts the full practitioner portal and Patient Copilot. Custom domain, custom theme, our infrastructure — no engineering work on your side.
Hosted
Integration spectrum
Choose how much of the experience you want to own.
Your infrastructure→Tera infrastructure
API
SDK
Hosted
API
SDK
Hosted
Your infrastructureTera infrastructure