Phirestream works with Apache Kafka to redact PII and PHI from data streams.



Phirestream identifies and redacts sensitive information such as PII and PHI from data in Apache Kafka.

The safest way to manage sensitive information in your systems is to apply safeguards before the the sensitive information enters your systems. Phirestream works with Apache Kafka to redact PHI and PII from your data streams.

Phirestream runs in your cloud. Your data never leaves your cloud and is not sent to any third-party.

Apache, Apache Kafka, Kafka, and associated open source project names are trademarks of the Apache Software Foundation.

Custom Lenses

Phirestream uses trained AI models called lenses.

Each lens is specially trained for different domains of text and can give Phirestream increased performance when deidentifying text in that domain.

You probably wouldn't want to try to deidentify healthcare text using a lens created for news, for instance!

Contact us to learn how to use a custom lens or to learn more about how we train and evaluate them.

General Lenses

Our general lenses are trained on a variety of text intended to be usable across multiple domains.

The general lenses include:

  • General
  • General (lite)

Philter uses a general lens by default.

Specialty Lenses

Our specialty lenses are trained on specific domains to increase Philter's performance when de-identifying text in those domains.

The specialty lenses include:

  • Healthcare (general)
  • Healthcare (COVID-19)
  • Legal (general)
  • Legal (contracts)
  • News (general)

Phirestream runs in your cloud and your data stays in your cloud.

Philter is available through the cloud marketplaces. All billing and procurement is conveniently handled via the cloud marketplace.

For managed services, other platforms, or Docker images please contact us.

See a Demo

Request a 30 minute demo to see Phirestream in action.

Request a Demo