Skip to main content

Data (PII) redaction

Moodi Mahmoudi avatar
Written by Moodi Mahmoudi
Updated over a week ago

At a glance

PII Redaction in NEXT AI automatically detects and replaces personal data across the system using either hashes (e.g., ####) or entity labels (e.g., [PERSON_NAME]). When enabled, detected PII is substituted in content and metadata; optional audio redaction can insert a “bleep.”

“Personal data” means any information relating to an identified or identifiable person (GDPR). “De-identification/redaction” removes or transforms identifiers to reduce re-identification risk (NIST).

How it works

  • Toggle PII Redaction on for your workspace or project.

  • When turned on, any detected PII information will be replaced:

    • With hash substitution: Hi, my name is ####!

    • With entity_name substitution: Hi, my name is [PERSON_NAME]!

You can also create redacted audio files to replace sensitive information with a beeping sound.

Example output:


Smoke from hundreds of wildfires in Canada is triggering air quality alerts throughout the US. Skylines from Maine to Maryland to Minnesota are gray and smoggy. And in some places, the air quality warnings include the warning to stay inside. We wanted to better understand what's happening here and why, so we called ##### #######, an ######### ######### in the ########## ## ################### ### ########### at ##### ####### ##########. Good morning, #########.Good morning. So what is it about the conditions right now that have caused this round of wildfires to affect so many people so far away? Well, there's a couple of things. The season has been pretty dry already, and then the fact that we're getting hit in the US. Is because there's a couple of weather systems that ...

PII policies covered

Policy name

Description

Example

account_number

Customer account or membership identification number

Policy No. 10042992; Member ID: HZ-5235-001

banking_information

Banking information, including account and routing numbers

blood_type

Blood type

O-, AB positive

credit_card_cvv

Credit card verification code

CVV: 080

credit_card_expiration

Expiration date of a credit card

credit_card_number

Credit card number

date

Specific calendar date

December 18

date_of_birth

Date of birth

Date of Birth: March 7, 1961

drivers_license

Driver’s license number

DL# 356933-540

drug

Medications, vitamins, or supplements

Advil, Acetaminophen, Panadol

email_address

Email address

event

Name of an event or holiday

Olympics, Yom Kippur

gender_sexuality

Terms indicating gender identity or sexual orientation, including slang terms

female, bisexual, trans

healthcare_number

Healthcare numbers and health plan beneficiary numbers

Policy No.: 5584-486-674-YM

injury

Bodily injury

I broke my arm, I have a sprained wrist

ip_address

Internet IP address, including IPv4 and IPv6 formats

192.168.0.1

language

Name of a natural language

Spanish, French

location

Any Location reference including mailing address, postal code, city, state, province, country, or coordinates.

Lake Victoria, 145 Windsor St., 90210

medical_condition

Name of a medical condition, disease, syndrome, deficit, or disorder

chronic fatigue syndrome, arrhythmia, depression

medical_process

Medical process, including treatments, procedures, and tests

heart surgery, CT scan

money_amount

Name and/or amount of currency

15 pesos, $94.50

nationality

Terms indicating nationality, ethnicity, or race

American, Asian, Caucasian

number_sequence

Numerical PII (including alphanumeric strings) that doesn’t fall under other categories

occupation

Job title or profession

professor, actors, engineer, CPA

organization

Name of an organization

CNN, McDonalds, University of Alaska, Northwest General Hospital

passport_number

Passport numbers, issued by any country

PA4568332, NU3C6L86S12

password

Account passwords, PINs, access keys, or verification answers

27%alfalfa, temp1234, My mother’s maiden name is Smith

person_age

Number associated with an age

27, 75

person_name

Name of a person

Bob, Doug Jones, Dr. Kay Martinez, MD

phone_number

Telephone or fax number

political_affiliation

Terms referring to a political party, movement, or ideology

Republican, Liberal

religion

Terms indicating religious affiliation

Hindu, Catholic

url

Internet addresses

ww.nextapp.co

us_social_security_number

Social Security Number or equivalent

username

Usernames, login names, or handles

@NEXTAI

vehicle_id

Vehicle identification numbers (VINs), vehicle serial numbers, and license plate numbers

5FNRL38918B111818, BIF7547

Redaction of audio files

NEXT also supports redaction on audio files to replace sensitive information with a beeping sound - like you hear audio "bleeped out" on TV shows and movies.

Note: Redacted audio creation is not supported for the EU region.

Availability

PII Redaction is included in all paid plans.

Standards alignment

Redaction supports GDPR’s personal-data handling and data-minimization goals, and follows de-identification guidance principles (NIST). Internally, NEXT AI’s Data Protection Policy requires handling in line with data classification and encryption controls.

FAQ

Q: What’s the difference between “hash” and “entity label” substitution?

Hashing replaces detected text with #### to remove content entirely; entity labels replace it with a type tag such as [EMAIL_ADDRESS] or [PERSON_NAME] to preserve context while hiding values.

Q: Where does redaction apply in NEXT AI?

The PII Redaction model is designed to minimize personal data across the system (content and associated fields) once enabled.

Q: What PII data does NEXT redact?

NEXT AI models redact a comprehensive set of entities: account_number, banking_information, blood_type, credit_card_cvv, credit_card_expiration, credit_card_number, date, date_of_birth, drivers_license, drug, email_address, event, gender_sexuality, healthcare_number, injury, ip_address, language, location, medical_condition, medical_process, money_amount, nationality, number_sequence, occupation, organization, passport_number, password, person_age, person_name, phone_number, political_affiliation, religion, url, us_social_security_number, username, and vehicle_id.

Q: Does NEXT AI PII redaction go beyond keyword matching?

Yes. NEXT AI uses context-aware models that look at the meaning and phrasing of text—not just lists or regex. It can redact PII when the context implies an identifier even without explicit keywords.

Example: “Is John still out of the office sick?” → “Is [PERSON_NAME] still out of the office [MEDICAL_CONDITION]?” (or with hashes: “Is #### still out of the office ####?”)

It also catches indirect patterns, e.g.

  • “Our CFO turns 60 next week.” → [OCCUPATION], [PERSON_AGE]

  • “Email me at jane at acme dot com.” → [EMAIL_ADDRESS]

Q: Does NEXT AI support audio redaction (“bleep”)?

Yes—NEXT can generate redacted audio that bleeps sensitive segments. EU region does not support this audio-creation feature.

Q: Is this the same as anonymization?

Redaction/de-identification removes or transforms identifiers to reduce re-identification risk, but anonymization has stricter expectations. See NISTIR 8053 for de-identification concepts.

Q: How does this relate to GDPR?

GDPR defines personal data broadly; redaction helps implement data-minimization and privacy-by-design practices by limiting exposure of identifiers.

Q: Is redaction tied to NEXT AI’s security policies?

Yes. NEXT’s Data Protection Policy requires protecting data per classification and encryption standards; redaction complements these controls.

Did this answer your question?