For your health — patient or professional
THE HARNESS
FOR YOUR HEALTH.
You already use AI for your health — asking about a symptom, a lab, a medication. So do your doctors, drafting the note and the prior auth. The harness is the layer that makes it accountable: your health conversations stay yours, and a licensed physician stands behind anything that matters.
Any model. A physician behind it. Yours by design.
New here? How the harness works, in 90 seconds →
Or see one for real — sign a document and verify it yourself →
AI drafts it in seconds — and it is held. No code path sends an unsigned draft to a patient, payer, or record.
Only now does it count — signed by a named physician, and provable years later.
Whoever you are, there's a door for you.
Everyone's health runs through AI now — the patient asking questions at midnight, the clinician drafting notes at scale. The harness is the same layer underneath both. Start where you fit.
Use AI for your health — safely, and privately.
Ask about a symptom, a lab, a medication. The harness keeps the conversation yours — not training data for a company you'll never meet — and puts a licensed physician behind the answers that matter.
- See your health dashboardApple Intelligence on your device + a physician where it counts→
- Why your AI health chats aren’t privateA 3-minute read that will change how you use ChatGPT→
- Find a licensed physicianEvery U.S. physician, searchable — no signup→
- Plan care for yourself or a parentWorker-owned care for aging at home→
- Keep your health record yoursA private health identity you carry→
Or tap Ask Vera (bottom-right) to ask a health question now — it's physician-governed, and it never trains on you.
Ship AI output you can sign, bill, and defend.
Bring any model your team already uses. Every clinically meaningful output is attested by a named physician — NPI-bound, hash-anchored, auditable — before it reaches a patient or a payer.
- Start a pilotSandbox today. Flat fee per review in production. A BAA before any patient data.→
- See the harness workLive demo — watch it block an unsafe summary→
- Why the law wants a human nowWISeR, seven 2026 state laws, the FDA paper — with sources→
- How it works, in 90 secondsDraft → signed → shipped, plainly→
- Score your AI governance12 questions, a scorecard you can keep→
- Earn from attestationReview AI output on your license→
“Companies need… a harness to orchestrate the whole thing.”
— Jensen Huang, CEO NVIDIA · June 2026WHAT WE BUILD
A physician attestation network, licensed where the patient lives (altru.care)
A peer-review marketplace with named clinicians (ClinicalSwipe)
An audit chain that links every AI output to the physician who attested it (Hashcare)
Domain-tuned agents for surgical practice, registry abstraction, and clinical documentation (SurgeonValue)
Together: the operational stack that makes physician-attested AI deployable at scale.
AI in healthcare has a governance problem.
Three failure modes are driving institutional anxiety about AI deployment.
Unsigned clinical output
AI drafts a care plan, a prior authorization letter, or a medication recommendation. Nobody reviews it. It reaches the patient. When something goes wrong, the liability chain is unclear.
Where the law now requires a signature →Credential laundering
An AI model trained on medical literature generates confident clinical language. No NPI number is attached. No licensed physician reviewed it. The clinical authority is borrowed from training data, not from a real doctor.
How an NPI gets bound to an output →Fragmented identity
A patient engages with AI across six different health apps. There is no unified identity, no shared medical context, no way for a physician to maintain a coherent longitudinal view of that patient's health journey.
Who owns the conversation →This isn't only our read. The World Economic Forum's 2026 AI at Work names accountability — not capability — the binding constraint on AI adoption in regulated industries, and economist Dan Davies calls the failure mode the “accountability sink”: a decision produced at machine speed that no one can be held to. The harness closes that gap — every clinically meaningful output is held until a named physician signs it, or it never ships.
The records already reach Claude. The output isn't governed.
Anthropic and connectors like HealthEx already bring a patient's consented records into Claude — securely, over the federal TEFCA network, via MCP, never used for training. That solves the input. What stays unsolved is the output: when the model interprets a lab, drafts a care plan, or suggests a medication, who signs it?
Consented records in
A patient connects their full history from 50,000+ provider organizations to Claude. Consent-scoped, never trained on. The input layer is solved — securely, over the federal TEFCA network.
See the connectorThe model reasons
The record becomes context. Claude can summarize it, explain a lab, draft a routine. Powerful — and, on its own, ungoverned for clinically meaningful output.
The published evidencePhysician-governed output
Before clinically meaningful output reaches a patient, a licensed physician attests it — NPI-bound, timestamped, audit-anchored. The layer the input pipes do not provide. This is us.
How the gate worksHealthEx put the patient back at the center of their data. The harness keeps a licensed physician at the center of the decision.
The architecture
The harness is the governance layer
you don't see.
Four components. One governed infrastructure. Every AI call in the ecosystem passes through all of them.
Independently proven at the frontier — June 2026
An open agent harness just carried a mid-tier model past the strongest frontier models on the hardest long-horizon engineering benchmark — same model, same budget, only the control loop changed. The lesson: independent verification, revisable planning, and disciplined stopping beat raw model strength on work that runs for days. But the control loop itself is now a commodity — every major model vendor ships an autonomous agent that will run a workflow end to end for a monthly fee. What does not commoditize is who the verifier is. Here it is a licensed physician, and the gate is attestation — the one part no vendor can rent you. Zenith, Frontier SWE →
NPI Registry
Every U.S. physician, live from CMS
Any NPI renders a page at harnesshealth.ai/dr/[NPI] on demand from the CMS NPPES registry — nothing is pre-indexed or stored. A physician claims a page by verifying the NPI and binding a signing key at /provider. No signup for a page to exist.
Search it →Attestation Engine
AI drafts. A physician attests. Cryptographic record.
Clinical output is held as a draft until a named physician signs it — NPI-bound, hashed, timestamped, and verifiable by anyone at /verify. Live as a working demonstration; the production review queue is in pilot.
Sign and verify a document yourself →Embed Network
45+ live sites on footer.js
One line of JavaScript. Patient intake, PROM collection, the on-site assistant, physician connection. Deployed across the ecosystem. Change once at the source — every site updates.
<script src="https://harnesshealth.ai/footer.js"></script>API Gateway
Every AI call is governed.
solvinghealth.com/api/chat — the governed Claude bridge. TLS-encrypted transport. Draft-until-attested gating. FHIR-aligned connectors (the Redox sandbox loop on SurgeonValue is the only live one). The intelligence layer is proprietary.
Programmatic access is a pilot conversation →For health systems
Two on-ramps. Less than one FTE to deploy.
Each on-ramp is a contained deployment designed to prove value inside existing CMS codes. No EMR rip-and-replace.
On-ramp 1
Post-surgical recovery
SurgeonValue and JointCoach handle prior auth, RTM billing (98985/98979), patient check-in, and outcome tracking. NPI is the login. AI drafts — the surgeon's name stays on the output. $51/patient/month in RTM (CPT 98975–98981), billed by the practice. A representative office example recovers about $147 in one routine follow-up — an example, not your number.
See SurgeonValueOn-ramp 2
Discharge-to-home
co-op.care deploys Vera AI for family assessment, autonomous LMN generation (HSA/FSA eligibility), and care coordination. Physician review built in — the reviewing physician is licensed where the patient lives. 3–5 minutes per attestation. Runs on existing CMS transition-of-care workflows.
See co-op.careThe same infrastructure. Four entry points.
Who are you? Each audience gets a different door into the same governance layer.
For Health Systems
Deploy physician-governed AI with a documented governance framework and a BAA offered to qualifying covered entities (none executed yet). Start in the sandbox; no EHR integration is live.
Evaluate for your health systemFor Physicians
Review AI-generated clinical documents between patients. Earn $12–100 per attestation. Your NPI is the credential. Your time is the inventory.
See how attestation worksFor Developers
Free pipes. Paid brain. FHIR connectors, EHR adapters, encrypted transport — the open layer. The intelligence layer, attestation network, and MCP server — proprietary.
Read the developer docsTrust and Governance
Draft-until-attested gating. The provisional patent draft (one application, not yet filed). The OIG Advisory Opinion 25-03 flat-fee reference. The governance documentation your legal team needs.
Review the governance modelLive infrastructure, not a roadmap.
What is deployed and running today. What is in process. The honest accounting is a governance signal, not a hedge.
- 45+ healthcare websites on footer.js
- Every U.S. physician searchable via the CMS NPI registry
- An MCP server for physician-governed AI tools
- Physician search at harnesshealth.ai/find
- chanio chat on every ecosystem site
- Patient PROM check-in (SMS delivery not yet live)
- EHR integration: designed, not built — the Redox sandbox loop on SurgeonValue is the only live connector
- Provisional patent: one application drafted, not yet filed
- BAA: offered to qualifying covered entities — none executed yet
- Production review queue: in pilot on ClinicalSwipe — the sandbox is open now
“The moat is whoever first connects grounded clinical evidence to native multimodal output, real workflow extensibility, and physician-earned trust.”
Techy Surgeon Substack, “Clinical AI Faceoff”, April 2026
We built the moat.
Who's accountable
A trust company signs its work.
Every attestation in the network traces to a named, NPI-verified physician — starting with ours.
Blaine Warkentine, MD
Founder
MD and clinical translator — two decades at the intersection of medicine and software, including the clinical strategy behind a $250M med-tech acquisition. Builds the harness in public.
blainomd.comMedical Director
Licensed where the patient lives
The medical director behind the attestation network — the NPI-verified signature on every Letter of Medical Necessity and clinical attestation. Named entity: altru.care.
altru.careQuestions a form can't answer? Use the BAA + evaluation request form.
The governance layer your AI deployment is missing.
Start with a BAA request or connect Claude to the harness. No sales call required.
We publish our system prompts, attestation rules, and audit log schema. Trust comes from showing the work.
HarnessHealth provides AI governance infrastructure for healthcare, not medical advice. All clinical outputs are supervised by licensed physicians. Consult a qualified healthcare provider for diagnosis and treatment.
HarnessHealth is an independent company. The harness is built on Claude, Anthropic's AI model, and is not affiliated with, endorsed by, or operated by Anthropic. The engine is theirs — the governance, the physicians, and the accountability are ours.