Skip to content
PII & DATA LOSS PREVENTION

Protect sensitive data in every prompt

Automatically detect and redact PII, API keys, and sensitive information before it reaches your LLM. Synthetic data replacement keeps context intact.

Start for FreeView Documentation
CANDIDATE, VALIDATED, ACTED ONfig. 01
matchedvalidatedaction4111 1111 1111 1111credit_cardluhn · passj.okafor@acme.exampleemailno checksum400 123 4567nhs_numbermod-11 · failactionper policydiscarded — not an identifierredact — defaultmasktokenize — reversibleblockor synthetic replacement — a fake value of the same shape, so the model keeps the context
A pattern match is a candidate, not a finding. Structured identifiers are checksum-validated — Luhn, IBAN mod-97, NHS mod-11, Verhoeff — so a number that merely looks like one is discarded instead of mangling your prompt.

What the DLP path does

01
43 PII Entity Types Detected
Comprehensive coverage across 11+ countries including SSNs, credit cards, IBANs, passport numbers, tax IDs, national health numbers, driving licenses, and more, with checksum validation for structured identifiers.
02
Synthetic Data Replacement
Replace real PII with realistic synthetic data to preserve context and model performance.
03
Secret Key Detection
Automatically detect and block API keys, tokens, and secrets from being sent to LLMs using entropy analysis and provider-specific pattern matching.
04
Custom Patterns
Add your own regex patterns to detect domain-specific sensitive data like internal IDs or codes.
05
Configurable Actions
Choose to redact, replace with synthetic data, or block requests containing sensitive information.
06
Compliance Ready
GDPR, CCPA, HIPAA-ready controls with audit logs and data handling documentation.

How PII Protection Works

  1. 01

    Detect

    ML models and pattern matching identify 43 entity types of PII across 11+ countries in incoming prompts.

  2. 02

    Redact or Replace

    Sensitive data is redacted or replaced with synthetic equivalents before reaching the LLM.

  3. 03

    Log & Comply

    All PII detections are logged for compliance. Original data never leaves your control.

Automatic PII Protection

python
# User input with sensitive data
user_input = """
Contact me at john.doe@company.com or 555-123-4567.
My SSN is 123-45-6789 and credit card is 4111-1111-1111-1111.
"""

# PromptGuard automatically protects
response = client.chat.completions.create(
    model="gpt-5-nano",
    messages=[{"role": "user", "content": user_input}]
)

# What the LLM sees:
# "Contact me at [EMAIL] or [PHONE].
#  My SSN is [SSN] and credit card is [CREDIT_CARD]."

# Or with synthetic replacement:
# "Contact me at jane.smith@example.com or 555-987-6543..."

Why PromptGuard DLP?

  • 43 PII entity types across 11+ countries
  • Synthetic data replacement preserves context
  • Zero-config protection
  • GDPR, CCPA, HIPAA ready
  • Included in all plans

Other controls on the same path

Protect Sensitive Data

Stop PII from leaking to LLMs. Automatic detection and protection in every request.

Get Started FreeContact Sales