AI Workspace for Healthcare Providers and Patient Information.
Summarise the discharge letter for ⟨PERSON_1⟩.
Add the AHV number ⟨AHV_1⟩ to the patient record.
Send the referral to ⟨EMAIL_1⟩ today.
Call the referring doctor on ⟨PHONE_1⟩.
Review the report from ⟨ORG_1⟩.
EU hostingStored in the European Union under the GDPR.
Swiss FADPSwiss data protection duties covered alongside.
No training, everA binding no-training instruction on every request.
Two hours of notes for every hour with a patient. The one tool that could give that time back is the one the record may never be shown to.
Medical confidentiality at risk
Art. 321, § 203 and Art. 226-13 bind the doctor, not the tool. A discharge letter pasted into a consumer AI tool is a disclosure to a third party.
Data used for training
Free chatbots may keep whatever is pasted into them, and a record does not stop being a patient’s because it was pasted.
Zero process visibility
No record of what left the practice, which model received it, what was masked, or under which rule. Nothing to show the patient who asks.
Every leading model, behind privacy infrastructure built in Switzerland for patient records
Mask sensitive patient data before it leaves. Patient names, AHV numbers, addresses, contact details, account details and other confidential information are replaced before the request reaches the AI model, then restored in the answer.
Every model, one subscription. GPT, Claude, Gemini and Mistral in one workspace. Use the model you want, or let Auto pick the best one for letters, referrals, literature research and everyday work.
AI that works with you. Hand Cedreon a piece of work, not only a question. Read the referral and the results, check the sources and draft the letter, behind the same vault.
The whole practice on one account, under rules the practice sets
Custom Guardrails
Set rules for what the practice may share with a model. Mark a patient number, a ward or a referring practice once and it stays hidden in every later chat. No member can loosen the practice’s rules.
Regions locked
One switch restricts the whole practice to models built and run in Europe, for the data protection officer who asks where a record is processed.
Check the list, then send
Attach a discharge letter, a referral or a lab report and Cedreon lists every value it will hide. Add any it missed, then send.
Organisation account
One admin console for the whole practice: add doctors, nurses and administrative staff, set the rules and the models once, and share the templates everyone writes from. Conversations stay each member’s own.
Seats on one invoice
Buy seats once. Invite the practice with a personal link; access activates on first sign-in. No IT project, no rollout.
Secrecy agreements, countersigned
Professional secrecy is national law, so we sign it with you where you practise: CH, DE, FR and more across Europe.
Which AI models can I use?
GPT, Claude, Gemini and Mistral, on one subscription and one invoice. Choose per conversation, or let Cedreon choose for you.
What exactly gets masked?
Names, organisations, AHV numbers, IBANs, card and patient numbers, addresses and references, plus anything your own rules add. Values are replaced before the request leaves us and restored in your answer. Detection is layered and best-effort: checksum patterns first, then a name recogniser that runs on our own servers.
Is our data used for training?
No. Every request carries an explicit no-training instruction, and the obligation is contractually binding on each provider we route to. How long a provider holds a request in its own operational logs is a separate question and varies by model.
Where is our data stored?
Your conversations, documents and audit chain are stored encrypted by Cedreon and never leave it in the clear. For the model itself, an organisation can lock its workspace to models built and processed in the EU.
How does billing work?
Seats, once, on one invoice for the whole practice. Every model is included, and new ones join your subscription as they ship. You start on a free allowance.
Can we see what the model actually received?
Yes. Every exchange lands on an append-only ledger: what was sent, what was hidden, and by which rule. When a patient asks what happened to their record, that is the answer.
How do we get started?
Create a free account and confirm your email address, then try it on a real case: summarise a discharge letter, draft a referral or compare two protocols. When you are ready, your admin buys seats and hands out access with a personal invitation link.
Is Cedreon only for hospitals?
No. Cedreon is built for anyone working with sensitive information, and in healthcare that includes hospitals, group and single practices, clinics and the administrative teams behind them.
Ready to use AI on a real case?
Join practices across Switzerland and Europe using Cedreon to work with the leading models without exposing patient data. Free to start.