TRUST IS THE OPERATING SYSTEM
OF MEDICINE.
We're building the infrastructure that protects it. Physician-attested AI orchestration with hard-intercept safety architecture and a 50-state attestation network. Open architecture. Audit chain. Cooperative governance.
WHAT WE BUILD
A 50-state physician attestation network (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.
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.
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.
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.
NPI Registry
2.4M licensed physicians
The CMS NPPES registry, pre-indexed. Every NPI maps to a page at harnesshealth.ai/dr/[NPI]. Physicians claim and enrich. Health systems query via API. Zero signup required for a physician to have a page.
Attestation Engine
AI generates. Physicians attest. Cryptographic record.
Every clinical output routes through the physician attestation queue. Reviewed in 3-5 minutes. NPI-bound. Authority consumption tracked to prevent rubber-stamping. Immutable audit log.
Embed Network
45+ live sites on footer.js
One line of JavaScript. Patient intake, PROM collection, Reed AI, physician connection. Deployed to 45+ sites. Change once at the source — every site updates.
<script src="https://harnesshealth.ai/footer.js"
data-npi="[NPI]"></script>API Gateway
Every AI call is governed.
solvinghealth.com/api/chat — the governed Claude bridge. HIPAA transport. SSO across all 45+ sites via Supabase. Hard intercept enforcement. Open-source FHIR connectors. Proprietary intelligence layer.
The same infrastructure. Four entry points.
Who are you? Each audience gets a different view of the same governance layer.
For Health Systems
Deploy physician-governed AI with a signed BAA, documented governance framework, and integration path to Epic, Cerner, and athena.
Evaluate for your health systemFor Physicians
Review AI-generated clinical documents between patients. Earn $12–400 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, HIPAA transport — MIT licensed. The intelligence layer, attestation network, and 231-tool MCP server — proprietary.
Read the developer docsTrust and Governance
The physician hard intercept. The provisional patents. The OIG Advisory Opinion 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
- 2.4 million NPI profiles indexed
- 231 AI tools in the MCP server
- Physician search at harnesshealth.ai/find
- Reed AI chat on every ecosystem site
- Patient PROM collection via SMS and web
- Chrome extension (Chanio) for ambient assistance
- EMR integration: Epic, Cerner, athena (in development)
- Provisional patents: 7 drafted (filing in process)
- FDA device registration: In progress for RTM billing compliance
- BAA: Available on request (2 business days)
- CMS ACCESS Model: Application submitted, Cohort 1 July 2026
“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.
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.