PERSONAL DATA MASKING PLATFORM

Keep your data useful.
Keep personal details private.

Mask personal data in text, documents and tables before it reaches AI, analytics and testing systems.

Start masking Plan a pilot

Optimized for TurkishConsistent tagsOne REST API

Z-Mask / Text processing EXAMPLE

ORIGINAL TEXT

Hello, I am Elif Şahin.
My phone number is 0532 123 45 67.
Email: elif@example.com

Detect · Validate · Mask

MASKED OUTPUT

Hello, I am [PERSON_1].
My phone number is [PHONE_1].
Email: [EMAIL_1]

WHEREVER DATA IS USEDAI workflowsDocument sharingTest environmentsData analytics

THREE NEEDS. ONE PLATFORM.

Control personal data in every format.

Text masking

Replace personal data in call notes, emails and complaints with consistent tags. Restore tagged AI responses using the mapping.

Documents and images

Read scanned pages. Redact personal fields, faces, signatures and QR codes, then download a masked PDF.

Tables and databases

Discover personal data columns automatically. Use format-preserving synthetic values, tags or partial masking.

SAAS · BATCH PROCESSING · REST API

Start in the workspace. Connect your workflow.

Use Z-Mask for a single text or a recurring data pipeline. The web workspace and API use the same masking services.

Web-based SaaS

Sign in to process text, PDFs, images or tables. Choose masking settings, download the output and review your processing history.

Open the workspace

Batch masking

Mask multiple texts in a JSON array with one request. Process many records in CSV, Excel and SQLite files using column-specific methods.

Try batch processing

REST API for your application

Send requests directly from CRM, document management, analytics and AI workflows. For document collections, build a workflow that submits each file in sequence.

Discuss API integration

From customer data to usable output

Receive data
Choose a masking policy
Process via API
Use the masked output

CRM notes → batch text masking · Document archive → per-file redaction · Test data → column masking · LLM → mask, then restore the response with a mapping

One request. Multiple texts.

POST /v1/mask accepts a texts array for batch processing. Use /v1/redact for PDFs and images, and /v1/table/profile and /v1/table/mask for tables.

The current SaaS API requires a signed-in user's access token and the project's publishable key. Handle token expiry and refresh in your integration. Keep passwords and server secrets out of client code.

Plan an integration pilot

REST API · cURL

ZMASK_API_URL="https://ownvacsoeaxuyrvipzxn.supabase.co/functions/v1/masking-gateway"

curl "$ZMASK_API_URL/v1/mask" \
  -H "Authorization: Bearer $ACCESS_TOKEN" \
  -H "apikey: $PUBLISHABLE_KEY" \
  -H "Content-Type: application/json" \
  --data '{"texts":["Elif Şahin, elif@example.com", "0532 123 45 67"],"return_mapping":false}'

Example data is fictional. Batch text uses one request; document collections require a separate request per file. Define volume, concurrency and integration requirements with us during a pilot.

PRACTICAL NEEDS, CONCRETE EXAMPLES

Preserve the meaning.
Control personal details.

From banking to healthcare and legal files to customer conversations: a masking workflow that keeps data useful.

Analyze the call note while keeping the customer's identity private.

ORIGINAL

Zeynep Kaya transferred TRY 18,750 from account TR84 0006 2015 8069 9833 9762 60 to Mert Çınar. Transaction date: 14 September 2026.

MASKED

[PERSON_1] transferred TRY 18,750 from account [IBAN_1] to [PERSON_2]. Transaction date: 14 September 2026.

The amount and transaction context are preserved; names and account details are tagged.

Examples use fictional data. Results vary with the selected data types and masking policy.

SECURE DATA FLOWS FOR AI

Send context to AI.
Keep identities within your organization.

Tag personal fields before calling a model for call summaries, email replies or document analysis. Restore response tags using the mapping data.

Receive data

Your application receives a call note, email or customer request.

Mask with Z-Mask

Selected fields become consistent tags such as [PERSON_1] and [PHONE_1].

Process with the model

A cloud or on-premises model generates a summary or reply from the masked content.

Restore the response

Use the mapping in your own workflow to restore tags to their original values.

Your organization manages access to mappings for reversible tagging. For test data, choose other methods such as synthetic values or hashes.

BEYOND TEXT: THE ENTIRE DOCUMENT

From scan to shareable PDF.

Read text with OCR and mask faces, signatures, QR codes and barcodes alongside personal fields. Review the boxes, add missing areas manually and download the result.

ID cards and passports

Names, ID numbers, dates of birth, photos and machine-readable passport fields.

Property deeds and powers of attorney

Rights holders, family details, identity fields and signatures in document-specific layouts.

Petitions and civil registers

Personal fields in dense text, multi-row tables and rotated scans.

Technical plans and forms

Headers, engineer names, phones, addresses and signatures while preserving the drawing's technical content.

RECOGNITION OPTIMIZED FOR TURKISH

Precise validation rules.
Flexible AI recognition.

A validation rule engine works alongside a multilingual recognition model. Personal details are masked while organization and place names remain readable.

Person nameTurkish national IDIBANPhoneEmailAddressCard numberDate of birthProperty

Custom entity types

Define your own data types without retraining or code changes.

By descriptionmedical diagnosis → [TESHIS_1]

By patternMN-482913 → [MUSTERI_NO_1]

By term listProject Kartal → [PROJE_1]

FROM PRODUCTION DATA TO TEST AND ANALYTICS DATA

The right method for each column.

Profile columns in CSV, Excel and SQLite files. Choose a method for each data type and use case; preserve relationships through consistent transformations.

Method	Example output	Use case
Synthetic value	`Büşra Orhan`	Realistic test data with valid formats for supported types.
Tag	`[PERSON_1]`	Track people and record relationships with readable tags.
Partial masking	`A* Y*`	Keep only the necessary part of a value visible.
Hash	`84b19…`	Create a consistent representation without revealing the original value.
Redaction	`████████`	Hide the field's contents entirely.

Column-level policies National ID, IBAN and card validation Consistent record mappings

INTEGRATE WITH YOUR EXISTING SYSTEMS

One API.
Multiple workflows.

Connect the workspace's masking engine to your own applications. Use a shared service layer for text, document and table processing.

Recognition and validation

Multilingual recognition with validation rules for Turkish national IDs, IBANs and card numbers.

Your organization's policies

New entity types through descriptions, regular expressions and term lists, with selectable types and thresholds.

Capacity-based deployment

Start with CPU, accelerate with GPU and process in parallel as needed. Measure capacity with your own data during a pilot.

YOUR INFRASTRUCTURE. YOUR CHOICE.

On-premises or as a service.

On-premises

Offline masking, local models and your own policies. Start with CPU and add GPU capacity as needed.

Private cloud

Run in your own cloud account. Scale capacity horizontally with stateless services.

SaaS

FROM PILOT TO PRODUCTION

Start with your own data.

Define success criteria together: which details to hide, which context to preserve and how to handle your workload.

Pilot

About 2 weeks

Measure recognition quality and speed with sample data; define entity types and masking policies.

Integration

About 2–4 weeks

Connect the API to authentication, LLM, document and database workflows.

Go live

About 1–2 weeks

Finalize deployment, capacity and monitoring, then bring real workloads online.

Continuous improvement

Throughout operation

Improve policies with new data types and tags; review quality periodically.

Timelines are indicative and will be agreed based on your scope and integration needs.

Let's discuss a pilot

COMMON QUESTIONS

A starting point
for your workflow.

Can I restore original values after masking?

When text tagging and mapping are enabled, use the mapping to restore tags. Synthetic values, hashes and redaction do not use this restoration workflow.

Can we define our own data types?

Yes. Use a regular expression for customer numbers, a term list for project names or a description-based entity type for diagnoses.

Can I review documents before sharing?

Compare original and masked pages, remove masking boxes or add new ones manually, then regenerate the PDF.

How are data and processing history handled?

The masking engine processes requests in memory. The SaaS workspace stores processing summaries and masked text history linked to your account; delete history entries from the workspace.

Can it run offline on-premises?

On-premises deployment with local models is supported. Hardware, capacity and integration requirements are evaluated during a pilot.

Mask personal data before sharing it.

Start a pilot with your own data.

Keep your data useful.Keep personal details private.