Protect sensitive data
Verillian scans outbound requests for regulated data and acts at the boundary, before content reaches the provider, rather than flagging it after the data has already left. Detection is configured per institution and is best-effort, not a guarantee that every value is caught.
What this looks like
Your policy is enforced at the moment a prompt is sent. Sensitive content is redacted or the request is blocked before it leaves the device.
- Before the boundary
- Configurable detection for social security numbers, payment card numbers, medical record numbers, and other types, applied in the request before it reaches the provider. Detection is best-effort, not a guarantee that every value is caught.
- Redact or block
- Per institution: which entity types, redact or block, and what sensitivity thresholds apply.
- Any HTTPS tool
- If the tool speaks HTTPS to a provider, Verillian governs it. No plugins, no API wrappers, no change to the tool.
- Provider receives only what policy allows
- Nothing more passes through than your rules permit.
Redacted before it leaves the device
Sensitive values detected in an outbound prompt are masked on the device before the request reaches the provider. Detection is configured per institution and is best-effort.
Summarize this patient’s history. SSN 123-45-6789, record MRN-4471902, seen for follow-up Tuesday.
Summarize this patient’s history. SSN •••-••-••••, record MRN-•••••••, seen for follow-up Tuesday.
redaction · representative view
Policy is checked and the interaction signed at the moment of execution, before anything leaves your network. Your keys, your record, your call.
Related problems
Most institutions arrive with one of these and find they have all four.
Run a pilot on your own fleet
We work closely with our first institutions, on their endpoints, against their policies. The deployment becomes the proof.