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.
Give every dietitian the reasoning of your best one.
Your dietitians already build plans. Clinical Reasoning interprets the labs and patient data behind those plans, and the protocol builders generate the personalized starting point — so the RDN (Registered Dietitian Nutritionist) spends the visit on judgment and the relationship rather than on assembly.
Practitioner-supervised. Rule-anchored. Evidence-cited. HIPAA (Health Insurance Portability and Accountability Act)-compliant, BAA (business associate agreement)-ready.
Get a demo
15+ hours
saved per practitioner per week on interpretation and plan assembly
3
knowledge bases behind every recommendation — biomarker to condition, condition to protocol, food to condition
7
protocol domains, so the plan extends past nutrition when the patient needs it to
The bottleneck isn't the dietitian. It's the hour before the visit.
Interpreting a panel, cross-referencing it against conditions, and assembling a personalized plan is the slowest part of the job — and the part where quality varies most between practitioners.
TODAY
Manual interpretation and assembly
Each RDN reads the labs, recalls the relevant evidence, and builds the plan by hand. Output quality tracks the individual practitioner’s experience, and throughput caps at how many plans one person can assemble in a day.
Scaling the practice means hiring more senior practitioners, because the reasoning lives in their heads rather than in the platform.
WITH TERA MODULES
Reasoning and protocols, generated
Clinical Reasoning maps the patient’s biomarkers and context to possible conditions deterministically, with a citation at every step — the RDN reviews findings rather than deriving them.
The Nutrition and Supplement builders generate a personalized, evidence-cited protocol the RDN edits and signs. Embed the Patient Copilot in your app and the plan runs daily between visits.
The modules this uses.
Interpretation, protocol generation, and a patient-facing surface to deliver the plan.
01
Clinical Reasoning
Maps biomarkers and patient context to possible conditions deterministically. The LLM (large language model) summarizes findings; the rules engine produces them.
02
Nutrition Protocol Builder
Biomarker-driven meal plans, foods used as medicine, eliminations, and macronutrient targets personalized to the patient’s diagnostic and goal context.
03
Supplement Stack Protocol Builder
Evidence-cited supplement stacks across cardiovascular, metabolic, hormonal, inflammatory, and longevity domains. Brand-aware.
04
Tera Patient Copilot
AI patient portal that coaches patients daily between visits. White-labeled (hosted by Tera) or embedded as an SDK (software development kit) in your patient app.
All nine modules are available — these are the ones this use case starts with.
How it works.
The practitioner stays in control at every step — the modules do the assembly, not the deciding.
Step 01
Patient data in
Labs, intake, and wearable data pass into Clinical Reasoning through the API or your existing integration.
Step 02
Findings, not guesses
The rules engine maps results to functional ranges and possible conditions. The model summarizes; it never interprets.
Step 03
Protocol generated
Nutrition and supplement protocols are generated against the findings, cited and personalized to the patient’s goals.
Step 04
RDN reviews and signs
Your dietitian edits and approves. The Patient Copilot then delivers the plan daily inside your app.
Safe AI architecture
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.
Clinical AI
Three layers of clinical defensibility.
Supervision
Reasoning
Evidence
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.
The architecture
Rules produce the findings. AI communicates them.
Practitioner supervised
Rule anchored
Evidence cited
Three ways to deploy.
Pick the integration depth that matches your engineering capacity and brand requirements. All three deliver the same clinical AI underneath.
— 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.
— 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.
— 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.
Same clinical AI underneath.
Choose how much of the interface and infrastructure your team wants to own.