Philter deidentifies and redacts sensitive information, such as Personally Identifiable Information (PII) and Protected Health Information (PHI),in text. Common uses of Philter include helping maintain HIPAA compliance, serving as an AI policy layer, redacting AI training data, and allowing for leveraging your text for valuable secondary purposes.

Philter can redact over 30 types of sensitive information, such as persons' names, ages, bitcoin addresses, cities, counties, credit cards, custom dictionaries, dates, drivers license numbers, email addresses, iban codes, ip addresses, mac addresses, passport numbers, phone/fax numbers, ssns and tins, shipping tracking numbers, states, urls, VINs, and zip codes. In addition, you can define your own types of sensitive information that Philter can then redact.

Philter can disambiguate between types of sensitive information allowing it to redact the information appropriately, and conditional statements allow you to redact only certain information, such as ages older or younger than a given value. Philter's Consistent Anonymization feature anonymizes information consistently across multiple documents to preserve meaning while removing personally identifiable information.

Philter is API based and open source client SDKs are available. The Philter Add-Ins for Microsoft Office provide redaction capabilities inside your Microsoft Word documents and Microsoft Excel documents.