Vertical AI for regulated healthcare, built on kOS
Running inside regulated healthcare today. Consent and consultation workflows, a health-data privacy posture, and decisions that carry an author, on the same platform every KlusAI use case lands on.
The vertical product sits on top of the platform. Identity, tenancy, audit trails and data residency are already underneath it.
Built for work that is regulated before it is automated
Every capability carries the obligation it has to satisfy. In healthcare the obligation usually arrives first.
Consent and consultation workflows
Record the consultation, transcribe it, check what the consent covers, and generate the consent document for signature.
The clinician signs; the platform shows what was covered and what was not.
Health-data privacy posture
Per-organization data residency, and a private mode that keeps inference on EU-resident compute instead of a cloud provider.
Where the data lives and where it is processed are both settings you can show.
Pseudonymisation before any model
Personal data is screened and pseudonymised before text reaches a model, and the check fails closed.
GDPR data minimisation applied at the boundary, not promised in a policy.
Decisions that carry an author
Every AI interaction records the actor and the model version, and changes to data wait for a person's approval.
A tamper-evident trail is what turns an AI decision into an auditable one.
Hospital systems that cannot leave your network connect through razorBridge Outpost, and private mode can run on an Outpost Blade on site.
How Outpost connectsScoped as a use case, not as a project
Two that run in production for clinics today, on the same platform every KlusAI use case lands on.
Informed consent, from conversation to signed document
The consultation is recorded and transcribed, the consent is checked against what was discussed, and the document is generated for signature.
See it on med.klusai.comPatient record, appointments and vaccinations in one place
One patient record with appointments and vaccination history beside it, scoped to the clinic that owns it.
See it on med.klusai.comThe de-identifier is ours, and it is measured in the open
Clinical text is its own problem: identifiers hide in dictated notes and free-text fields, and a redaction that leaks one national ID has failed. Our research de-identifier is measured on EuroPriv-Bench, our open benchmark, in 8 EU languages. In production, kOS screens and pseudonymises personal data with a check that fails closed.
See the researchNational-ID leakage, lower is better
EuroPriv-Bench, verified July 26, 2026.
What the AI may touch is a setting, not a convention
Every tool the assistant can reach is declared: what it reads, what it writes, and which actions stop for a human to confirm. An organization handling patient data can show its regulator the configuration rather than describe the intent.
In production, not in decks
Informed consent runs in production on kOS, at med.klusai.com.
Consultations recorded and transcribed, consent checked against what was discussed, and the document generated for signature, under the privacy and audit obligations the sector actually carries.
A KlusAI vertical product on the same platform as every use case.
Vertical AI products, built with domain partners
We build AI-native products for regulated European industries together with partners who own the domain expertise. Healthcare is the second vertical, and the model is the same one legal and notarial runs on.
The partner brings
- Domain expertise
- Distribution and customer relationships
- The regulatory reality of the practice
KlusAI brings
- kOS, in production and audited
- Research models, including kp-deid
- Delivery, at a fixed fee per use case
Both hold
- A shared product
- Shared upside
- An IP model agreed before work starts
Own a healthcare domain?
Bring the domain. We bring the platform, the models and the delivery.
Message received!
We'll send you a confirmation email shortly.
Want to track your inquiry and access exclusive content?
Create your KlusAI accountStay in the loop
Weekly insights on production AI. No hype, just what works.
Follow us on LinkedIn
Stay updated on our latest AI work and insights.