How it works
Suvard sits in the path of the AI traffic, between your staff and systems on one side and the AI models on the other. Every request goes through the same four steps, in every sector. Only the detector changes.
what must never leave the building: names, CPR numbers, addresses, account numbers, diagnoses. Also what no list knows, with a detector trained for the sector.
the findings with placeholders before the AI sees them. The user sees what was found and approves it. No new workflow.
what must not happen, by your own rules: who may send what to which model.
every event in a signed chain where later changes can be detected, and which others can verify without trusting us.
Where does it sit?
Chat, drafts, decision support, agents. The workflow does not change; the user only sees what was masked.
Finds, masks, stops, seals. The keys are yours. No content leaves the building, and nothing is sent to us.
ChatGPT, Claude, Gemini, Copilot, or a model in your own data centre. We never supply the language model itself.
Evidence is only truly independent if the entity sealing it has no stake in the outcome. That is why Suvard sits outside both the workflow and the model.
An example from healthcare
The same question to the AI, but without anything that can identify the patient. The user sees the findings and approves the placeholders before anything is sent.
Draft a discharge summary for Jens Hansen, CPR 010190-1234, Vestergade 12, Aalborg, admitted with atrial fibrillation, treated with Marevan.
Draft a discharge summary for [NAME], CPR [CPR][ADDRESS], admitted with [DIAGNOSIS], treated with [MEDICATION].
The healthcare detector is a Danish clinical language model, trained without a single patient record, plus CPR number checks. In energy, finance, legal, defence, space and the public sector it is the same four steps with another detector, when we get there.
The evidence
Each event points to the previous one using a cryptographic fingerprint. If a single line is deleted or altered, the chain breaks, and the tampering is immediately evident.
The seal is signed using keys held by you, not by us. What is sealed is the proof of what occurred, never the content itself.
A small, standalone utility with no dependencies can verify the seal offline. Anyone can run it. That is what makes the independence more than a promise.
The same seal can be applied to non-conversational AI, such as draft entries in the EHR or decision support within the line-of-business system binding the AI's output and the human action into a single event. That is the evidence layer; fully built and currently piloting.
Questions we hear
No. Suvard is installed on your own network, on your own infrastructure. Nothing sensitive leaves the building. That is the whole point.
No. Suvard sits in front of the AI services your staff already use. Local models are an option, never a requirement. We never supply the language model itself.
Suvard sits in the path of the traffic as a proxy and is therefore vendor-independent: ChatGPT, Claude, Gemini, Copilot and AI built into line-of-business systems. Same engine, same evidence.
Healthcare, through CareProxy: the engine with Danish clinical detection, masking and a signed log is validated in Treat Systems' technical environment, and we are in dialogue with a Danish region. The evidence layer (the independent seal) is built and in a pilot phase. Detectors for energy, finance, legal, defence and the public sector are not built yet; the engine is the same.
No tool can promise that. Suvard supports compliance: it enforces your rules technically and produces the evidence. The legal assessment remains yours.
A hash-chained, signed log of every AI request and every decision, which can be exported and verified with a small, standalone program, without trusting us.
A firewall sees packets; classic DLP sees patterns. Suvard understands what is being sent to AI: it masks it with placeholders people can keep working with, stops what must never leave the building, and proves afterwards what happened.
A conversation, a mapping of your actual AI use, and then a pilot in your own environment. Write to matias@suvard.com.
Next step
We start with a mapping, not a sale. You get an honest picture of what passes through your network, and what it would take to be able to prove it afterwards.