Consulting
Bring in the team that built the software. We assess what you need and deliver an implementation plan, then either build it inside your own cloud or hand it to your engineers to build. Either way you end up with a system you own outright.
Engagements are led by Jeff Zemerick, the creator of Philter and the Philterd open source toolkit. You get the person who wrote the code, not a sales engineer reading from a runbook. We have deployed redaction pipelines processing millions of records daily across healthcare, financial services, and government, including PHI redaction projects under HIPAA.
Four steps, from the first call to a system you own.
A 30-minute call to learn about your PII redaction requirements: what you need to protect, which regulations apply, and what you are running today. No slides, no pitch.
You come away knowing whether we are a fit and what a Discovery would cover. If the open source toolkit on its own is all you need, we will tell you that and point you at the right starting point.
We get into the details over a few meetings: a deep dive into your data, your systems, and your compliance obligations. You come away with two deliverables, a detailed assessment of your PII redaction needs and an implementation plan.
The implementation plan is yours either way. Some clients hand it to their own engineers and build it themselves. Others bring us in for the build. That choice is yours to make, not a condition of the engagement.
We build out the design from the Discovery, inside your own cloud. Your data stays inside your perimeter for the whole build. There is nothing to ship to us.
You see every step and nothing is a black box. The software is open source and the configuration is yours to read. If you have an engineering team, they can work alongside us so the knowledge transfers as the system goes up.
You own the system outright: the open source software, the infrastructure, and the operational knowledge.
We hand over the policies, the configuration, and a runbook for tuning as your data changes, so your team can run and adjust it without us. We stay available whenever you want us back, for a policy question a year later or a second pipeline.
Want to see a specific engagement end to end? AI training-data de-identification walks through the phases, the deliverables you keep, how your data is handled, and how we scope it.
Three ways we plug in, from a full build to training models on your data.
We stand up PII redaction in your own cloud, configure and validate it on your data, then hand you a running system you own. No in-house engineering team required. If you would rather build from the Discovery plan yourself, that works too.
We design end-to-end PII protection for your data and AI workloads: data flows, redaction layers, audit trails, and the guardrails that keep generative-AI features aligned with HIPAA, GDPR, and CCPA.
Off-the-shelf models miss the identifiers that matter most in your domain. We train specialized PII and PHI detectors on your data, measured against precision and recall you can put in front of an auditor.
We work across regulated industries where a PII leak carries real consequences.
PCI scope reduction, GLBA compliance, PII redaction for banking and fintech data flows.
HIPAA Safe Harbor de-identification, clinical NLP, PHI redaction for research and analytics pipelines.
Court filing redaction, e-discovery, FRBP 9037 compliance for law firms and legal tech.
FOIA processing, FedRAMP-ready deployments, GovCloud and air-gapped environments.
LLM prompt guardrails, RAG pipeline redaction, training data de-identification.
Claims processing, underwriting pipelines, GLBA and NAIC compliance.
Three principles shape everything we build: your data never leaves your perimeter, the engine is open source and auditable, and the models are purpose-built for PII and PHI.
Philter and the rest of the Philterd toolkit run inside your own environment, whether that is your cloud, your own servers, or your desktop. Your data stays in your perimeter, never reaches a third-party API, and never lands in someone else's logs.
Transparency is the only way to verify privacy software. Our core engine is Apache 2.0 licensed, so your engineers can read every line, audit every decision, and extend the stack on their own terms.
Generic LLMs make poor privacy filters. We train and ship specialized NLP and deep-learning models built specifically for PII and PHI detection. They are accurate, tunable, and operationally affordable at scale.
A few engagements we have delivered.
A law firm with no in-house engineers needed PII removed from federal bankruptcy filings under Rule 9037. We designed the redaction, stood up the AWS deployment, and handed back a system that redacts documents automatically as staff save them.
Read the case study →Embedded real-time PII redaction into a bilingual (English/French) patient chatbot so sensitive information is stripped before messages reach human agents or analytics storage.
Read the case study →Deployed Philter inside an AWS data pipeline to de-identify clinical narrative text flowing from an EHR into an analytics database, enabling research access without HIPAA restrictions.
Read the case study →Describe the sensitive data your firm handles and we'll show you how we'd set up redaction in your environment. We'll get back to you within one business day.