AWS Marketplace
Azure Marketplace
Google Cloud MarketplaceClaims and underwriting text
Redact names, contact details, Social Security numbers, and addresses from claims notes, adjuster narratives, and underwriting files, so they can feed analytics, AI features, and data sharing.
Carriers and independent agencies
PII Redaction for Insurance
Redact customer details from claims notes, underwriting files, and transcripts as they move through your systems, or from documents on a single PC. An injury or disability claim can put medical records in the same file as a policyholder’s financial details, so one claim may need more than one kind of redaction.
For carriers and claims operations
What Philterd does with policyholder data
Social Security numbers on forms and letters
Many states restrict displaying Social Security numbers, as California Civil Code 1798.85 does. Philter can redact an SSN entirely, or keep only the last four digits on documents that still need to identify the policyholder.
Starts from GLBA, and HIPAA where health data appears
The policy library has a GLBA nonpublic personal information policy, and a HIPAA Safe Harbor policy for claims that carry health information. Both are starting points to adjust for your own claim and policy number formats.
Which fits your organization
A carrier or claims operation
Philter
Redacts claims notes, adjuster narratives, and call transcripts through an API in your own cloud, before they reach analytics, AI features, or partners.
About Philter →An independent agency
Philter Desktop
Redact claims, applications, and loss runs on a Windows PC before they go to a carrier or a customer. No server to set up, and no uploads.
About Philter Desktop →An agency sharing the work
Philter One
Coming in the first half of 2027. A small computer on the agency network that every producer and CSR uses from a web browser, with a person’s review before every redacted copy.
Join the list →A team that wants it built
PII Data Pipelines
We design the redaction for your claims and policy data, build it inside your cloud, measure it on real claims, and hand you a system you own.
See the engagement →Getting started at a carrier
- Deploy Philter from your cloud’s marketplace into the cloud account next to your claims system.
- Start from the GLBA policy in the policy library, and add patterns for your own claim, policy, and member number formats.
- Measure it on your own claims. Have an adjuster mark a sample of claims, then score the policy against it with Philter Scope, paying attention to claim and policy numbers that look like phone numbers.
- Start with the files that leave the company, such as packages for reinsurers, outside counsel, and data partners, then move on to claims notes and call transcripts.
Ready-to-use redaction policies
Free, ready-to-use policies from the open source policy library. Download and load into your Philter instance.
Finance
v2.0.0
GLBA Nonpublic Personal Information (NPPI) Redaction
Redact Nonpublic Personal Information (NPPI) from financial customer records under the Gramm-Leach-Bliley Act (15 USC 6801-6809).
Healthcare
v2.0.1
HIPAA Safe Harbor De-Identification
A starting point for HIPAA Safe Harbor de-identification of clinical text per 45 CFR 164.514(b)(2).
General
v2.0.0
CCPA / CPRA Consumer Privacy Redaction
Redact personal information and sensitive personal information as defined by the California Consumer Privacy Act (CCPA/CPRA) from consumer records.
Recent writing on insurance
Redaction for Insurance: Claims, Customer Data, and the State-by-State Patchwork
Insurance carriers sit at the intersection of GLBA, HIPAA, state rules, and the NAIC Model Law. A guide to redacting NPPI and PHI in claims and adjuster notes.
Automatically Redacting PII and PHI from Files in Amazon S3 using Amazon Macie and Philter
Use Amazon Macie to find sensitive data in S3, then automatically redact PII and PHI such as SSNs and phone numbers from those files with Philter.
Redact PDFs Offline on Windows so No Data Leaves Your PC
Philter Desktop redacts PDFs entirely on your Windows PC, including scanned pages read with on-device OCR. No uploads, no server, and it works offline.