Applications pillar · LLM privacy gateway

The PII firewall for your AI pipeline.

One API call masks names, emails, and SSNs, plus what every other tool misses: API keys, JWTs, and session tokens. Reversible placeholders keep your workflow intact, and your users never notice.

You are wiring LLMs into support tickets, logs, and chat, and compliance is asking what happens to customer data inside those prompts. Regex is a leaky bucket, and self-hosting an NER stack is a project nobody has time to babysit.

curl https://api.shroudcloud.com/v1/shroud \
  -H "Authorization: Bearer ***" \
  -d '{"text": "Card on file for Maria Gonzalez, contact [email protected], session eyJhbGciOi..."}'
{
  "text": "Card on file for [PERSON_1], contact [EMAIL_1], session [JWT_1]",
  "entities": 3,
  "reversible": true
}
Call /v1/unshroud with the mapping to restore real values in the model's response.

What it catches

Standard PII

Names, emails, phone numbers, SSNs, addresses, dates of birth. The baseline every tool claims.

Identity artifacts

Bearer tokens, JWTs, OAuth codes, API keys, session cookies. The things an identity researcher knows leak.

Secrets

Private key blocks, AWS access keys, generic high-entropy API key patterns, with context-word scoring around each.

How it works

1. Shroud

Send text. Get back deterministic placeholders — [PERSON_1], [EMAIL_1], [JWT_1] — with a structured entity map.

2. Let the model work

The LLM reasons over placeholders, never real data. Context stays intact because replacements are deterministic.

3. Unshroud

On the response, swap placeholders back. Your end user sees real data; the model never did.

FAQ

Is this a self-hosted or managed service?

Managed API with zero retention: text is processed in memory and destroyed. Nothing is stored, logged, or used for training.

Does it work with streaming responses?

Yes. The shroud/unshroud mapping is stateless per request and works on streamed chunks.

What about pricing?

No pricing announced yet. Early access users set the roadmap and lock in founding terms.