PrivacyLayerRequest a demo

Data protection for authorised AI applications

Protect sensitive data across AI workflows.

PrivacyLayer is a proposed data protection layer that sits between your application and the model. It finds personal and confidential information in prompts and responses and applies your organisation’s own masking and redaction policy — before anything leaves your control.

01 · Live playground

Paste a prompt. Choose a policy. Watch it change.

This runs the prototype’s detectors in your browser — nothing is sent anywhere. Edit the synthetic text or change what happens to each type of data.

Output · sent to the model Restricted

Hi, I'm Adaeze Okafor (a••••••••••••@example.com, •••• ••• 0142). My card •••• •••• •••• 1111 was charged twice on order [ID]. Please refund to account ••••••6789. I was diagnosed with [HEALTH] last year, so the pharmacy delivery matters. My ID number is [ID] and my date of birth is [DOB]. Test key: [SECRET].

Policy per entity
Email address
Phone number
Payment card
Bank account
ID number
Date of birth
Person name
Health information
Credential / API key

10 detections · 9 protected

02 · Core features

Hover to declassify.

01

Sensitive information classification

Every request is labelled Public, Internal, Confidential or Restricted from what it contains, so policies and alerts can follow the level.

02

Personal identifier detection

Emails, phone numbers, Luhn-checked cards, account and ID numbers, dates of birth, names, health terms and credentials — each with a confidence.

03

Data masking and redaction

Mask (keep the last four), redact to a label, hash to a stable pseudonym or allow — chosen per entity type.

04

AI application privacy monitoring

Watch what flows into prompts and out of responses, by application, so leaks in model output are caught too.

05

Organisation-specific privacy policies

Start from a fintech, healthcare or analytics profile and tune it; restricted data can only be allowed with a written reason.

06

Audit logs and privacy dashboards

Counts, actions and levels for every call — metadata and a fingerprint only, never the raw text.

07

Privacy integration API

One authenticated call before the model and one after. Same policy, same log, any provider.

03 · The differentiator

Designed for AI inputs and outputs.

A configurable data protection layer built specifically for authorised AI application inputs and outputs. Prompts are cleaned before they reach the model; responses are checked before they reach the user.

→ Input

“My card 4111 1111 1111 1111 was charged twice.”

→ “My card •••• •••• •••• 1111 was charged twice.”

← Output

“I’ll refund it to account 0123456789.”

← “I’ll refund it to account ••••••6789.”

04 · Who it’s for

Teams shipping AI on sensitive data.

{ }

AI SaaS developers

Add a privacy layer to every model call without rebuilding your stack.

₦

Fintech companies

Keep card, account and identity numbers out of prompts and logs.

+

Healthcare technology providers

Pseudonymise patients and health details before summarisation.

Decision-makers CTOs Data protection officers Enterprise security managers

05 · Business model

Pay for what you process.

Usage-based subscriptions tied to processed data volume, with enterprise functionality — custom detectors, single sign-on, customer-managed keys and dedicated support — in a higher tier. Illustrative pricing for a proposed product.

$390 / month

$250 including 10M characters + 10M at $14 per million.

Request a demo

06 · Planned AWS infrastructure

How we use Amazon Web Services.

PrivacyLayer is a proposed data protection layer for AI applications run by AI SaaS developers, fintech companies and healthcare technology providers. It must inspect text on its way into and out of AI models in milliseconds, apply each organisation’s own policy, and keep tamper-evident metadata without storing sensitive content. Designing on AWS lets it use managed PII detection and guardrails behind an authenticated API, with keys under customer control.

  1. 01

    Request in

    Amazon API Gateway

    Applications send prompts and model responses to an authenticated privacy API.

  2. 02

    Detect

    Amazon Comprehend

    Personal information is identified and located in the text, alongside custom detectors for each organisation.

  3. 03

    Apply policy

    AWS Lambda

    Each entity is masked, redacted, hashed or allowed according to the organisation’s policy.

  4. 04

    Guard the model

    Amazon Bedrock Guardrails

    Configurable protections filter sensitive content in inputs and outputs of Bedrock-hosted models.

  5. 05

    Record

    Amazon DynamoDBAWS KMS

    Policies and audit metadata are stored, encrypted with customer-managed keys; raw text is never kept.

Across every stage
  • AWS KMS manages customer encryption keys
  • AWS Lambda runs detection and redaction
  • Amazon Cognito authenticates console users and roles
  • AWS CloudTrail records administrative access

Services and their role in PrivacyLayer

Amazon Comprehend
Identifies and locates personal information in text.
Amazon Bedrock Guardrails
Applies configurable content protections to model inputs and outputs.
Amazon API Gateway
Provides the authenticated privacy processing API.
AWS Lambda
Runs detection, policy application and redaction.
Amazon DynamoDB
Stores privacy policies, allowlists and audit metadata.
AWS KMS
Manages the encryption keys for policies and metadata.
Amazon Cognito
Authenticates console users and enforces roles.
AWS CloudTrail
Keeps an audit trail of administrative actions.
AWS Activate · company description

PrivacyLayer is a proposed AI data protection platform for organisations developing and operating AI applications. The planned product will identify sensitive information, apply configurable redaction policies and support privacy monitoring within authorised application workflows. Amazon Comprehend will assist with personal information detection, and Amazon Bedrock Guardrails will support configurable application protections. We plan to use Amazon API Gateway and AWS Lambda for processing, Amazon DynamoDB for policy management and audit metadata, and AWS KMS for encryption. Organisations will configure their own privacy requirements and review detection accuracy before production deployment.

Planned, not yet deployed. This website and the privacy console run in your browser on synthetic text.

Founder

Elizabeth Chinedu

Elizabeth founded PrivacyLayer after seeing product teams pause promising AI features because nobody could say what personal data was flowing into prompts and out of responses. Elizabeth leads product, customers and every pilot, with a focus on configurable, measurable protection.

  • Product
  • Data protection for AI
  • Customer pilots

07 · Progress & demos

See your prompts, protected.

PrivacyLayer is a proposed product in its building stage. A demo walks through detection, policies, output checks and review on synthetic text. The MVP covers synthetic text analysis, configurable redaction rules, privacy review reports and an authenticated data protection API.

  1. 2026
    Company founded

    By Elizabeth Chinedu, to let teams use AI without sending personal data where it shouldn’t go.

  2. Done
    Protection model defined

    Detect, classify, apply per-entity policies on inputs and outputs, log metadata only, review accuracy before production.

  3. Done
    Privacy console prototype

    Live redaction, configurable policies, false-positive review, dashboards, audit log and API examples on synthetic text.

  4. Done
    AWS reference architecture

    PII detection, guardrails, processing API, policy store and key management designed.

We use these details only to respond to your request. See the privacy notice.

FAQ

Questions engineers ask.

Does PrivacyLayer store our prompts?

No. The audit log keeps counts, actions, the sensitivity level and a fingerprint of the protected output — never the raw text.

Which data can it detect?

The prototype detects emails, phone numbers, Luhn-checked payment cards, bank account and ID numbers, dates of birth, names from a list, health terms and API keys. The planned product adds Amazon Comprehend and organisation-specific detectors.

How accurate is it?

Accuracy depends on your data, which is why every organisation reviews detections on synthetic data first and feeds false positives back into its policy.

Is PrivacyLayer live?

Not yet. It is a proposed product; the privacy console is a prototype running in your browser on synthetic text.

Contact

Talk to PrivacyLayer.

Questions about the product, the API and integrations, security, or partnerships. Messages go directly to the founder.

elizabeth@privacylayer.site