> For the complete documentation index, see [llms.txt](https://docs.satisfilabs.com/resource-center/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.satisfilabs.com/resource-center/system-updates-and-support/release-notes/security-and-privacy-product-updates/pii-security-redaction-profiles.md).
# PII Security - Redaction Profiles
### Overview
We’ve made enhancements to PII redaction components. You can now choose your level of PII control based on your organization’s security and privacy requirements.
These updates determine how potentially sensitive information is handled across the Satisfi Labs platform by scanning inbound chat messages before any processing occurs.
The goal:
* Reduce exposure to sensitive user data
* Give you more control over security posture
* Improve trust and compliance readiness
* Strengthen protections without changing the user experience
This is a configuration-level enhancement, no implementation work or code changes are required from you.
### What’s new
**Enhanced Protection for Free-Text Chat Inputs**
Our latest enhancements introduce configurable redaction profiles, giving you greater control over how sensitive information is handled.
Supported detections include:
* Email addresses
* Phone numbers
* Dates of birth
* IPv4 addresses
* Social Security Numbers
* Credit card numbers
* Bank account numbers
Depending on the type of information detected, the platform will either:
* Partially redact the sensitive portion of the message, or
* Fully redact the message if highly sensitive information is detected
Partially redacted messages are processed with the sensitive information masked. Fully redacted messages are not processed by downstream systems.
### Options to Have
You can now choose between two PII Redaction Profiles depending on the security preferences.
| Default Profile | Enhanced Protection Profile |
| ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| What gets blocked/redacted:
- SSNs → Full rejection
- Credit cards → Full rejection
- Bank accounts → Full rejection
- DOBs → Partial redaction
- IPv4 addresses → Partial redaction
| What gets blocked/redacted:
- SSNs → Full rejection
- Credit cards → Full rejection
- Bank accounts → Full rejection
- DOBs → Partial redaction
- IPv4 addresses → Partial redaction
- Email addresses → Partial redaction
- Phone numbers → Partial redaction
|
| What still passes through:
- Email addresses
- Phone numbers
| - |
| Recommended for clients that:
- Want standard PII protection
- Still rely on email/phone visibility in workflows or transcripts
| Recommended for clients that:
- Treat email and phone as sensitive data
- Have stricter compliance/security policies
- Want maximum PII protection across AI and analytics workflows
|
### How to Install
The default profile is already applied to your account. [Create a support ticket](https://satisfi-labs.atlassian.net/servicedesk/customer/portal/10) to switch to an enhanced redaction profile.
### Common Questions
Do I have to do anything if I am ok with the default profile?
No action is required if you select the default profile.
Your account will continue using the standard PII redaction settings automatically. If your organization later requires stricter privacy controls, we can easily switch your account to the enhanced redaction profile through a simple configuration update.
Does redacting information impact how our agent answers?
Yes, redaction may impact how the agent responds, depending on the level of redaction applied.
With partial redaction, the agent will still process the message, but certain sensitive portions of the input will be masked. This means the agent may only see part of the user’s original message when generating a response.
With full redaction, the message will not be processed at all because highly sensitive information was detected. In these cases, the agent will not be able to respond to the request until the user revises and resubmits their message.
Whenever either condition is triggered, the user will receive a notification explaining that sensitive information was detected and prompting them to update and resend their request.
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter:
```
GET https://docs.satisfilabs.com/resource-center/system-updates-and-support/release-notes/security-and-privacy-product-updates/pii-security-redaction-profiles.md?ask=
```
The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.