AI for CVs and payroll, without employee details leaving the company.

A CV is a file of personal data

The CV you “summarise” in a chatbot carries a name, an address, an age, a phone number and a history. Under the GDPR that is a transfer to a third party, usually outside the EU.

Payroll and sick leave are special categories

Pay, social security numbers, medical notes and union membership need a stricter legal basis. They do not belong in a prompt.

The employee has a right to know

If they ask “what did you send about me to an AI?”, HR must answer with a record, not a guess.

What gets detected

What gets detected in your documents

Greek-specific identifiers

• Tax ID (ΑΦΜ) — Greek tax identification number with modulo-11 check digit validation, not a bare 9-digit match. (check: modulo 11)
• Social security (ΑΜΚΑ) — Greek social-security number with Luhn and birth-date validation. (check: Luhn)
• ID card number — Greek police ID card, old and new formats (letters and digits). (check: μορφή)
• myDATA and EFKA registries — AADE myDATA MARK and invoice UID, EFKA employer and insured numbers (ΑΜΕ, ΑΜΟΕ). (check: συμφραζόμενα)

European and international

• IBAN — Bank accounts of every EU/EEA country with MOD-97 validation. (check: MOD-97)
• National IDs (EU, US, UK) — DNI, PESEL, Codice Fiscale, NIR, SSN/ITIN/EIN, National Insurance and more. (check: εθνικοί έλεγχοι)
• Passports — Passport numbers, context-gated in 24 EU languages. (check: συμφραζόμενα)
• Phone numbers — Landlines and mobiles for the EU, UK, US/Canada and Switzerland, validated per country. (check: libphonenumber)
• Postal codes — Greek postcodes, US ZIP codes and UK postcodes. (check: συμφραζόμενα)

People and contact details

• Names across grammatical cases — Greek NER that follows inflection, greeklish spellings and links the forms of the same person.
• Email addresses — Email addresses. (check: μορφή)
• Street addresses — Street, number and area, in Greek and Latin-script text.
• Dates — Birth dates and other identifying dates. (check: μορφή)

Health and special categories

• Medical data — Conditions, medication, blood type, record, insurance and prescription numbers, ICD-10 codes.
• Special categories — Religion, nationality, political and trade-union references, marital status, profession.

In scanned PDFs and images, signatures and stamps are covered by visual redaction, with a preview before it is applied.

Every category and the accuracy measurements

How it works, in three steps

Paste or upload

A CV as PDF or Word, a payroll table as text, a candidate email. You see the findings before anything leaves.

Placeholders reach the AI

“Candidate [NAME_1], born [DOB_1], ΑΜΚΑ [AMKA_1]”. The model summarises, compares or drafts without receiving the details.

The answer returns complete

The summary, the offer letter or the reply to the employee comes back with the real data, in your own account.

Data masking for documents

CVs, contracts, certificates: preview of findings, export, restore.

Email assistant

Gmail and Outlook: candidate correspondence is pseudonymised before the AI, the draft returns complete for you to review and send.

Policy for the department

Mandatory categories (tax ids, ΑΜΚΑ, health data always masked), roles, PII-free reports.

The ChatGPT & Claude you already have

A browser extension that masks the moment you press Enter, or a Windows desktop agent for every application.

What you answer the DPO

• Pseudonymisation by default: the measure the GDPR names explicitly in Articles 25 and 32.
• Special categories (Article 9): health data and union membership are detected and masked as a mandatory organisation policy.
• Mapping encrypted on EU infrastructure, per company account.
• A record per conversation and an evidence pack: answer an employee access request with facts, not a guess.

Guides for the GDPR file

GDPR checklist for AI tools in a Greek office

12 points with the articles next to each, a one-page AI-use policy template, what to mask. Greek.

Read PDF

Frequently asked

Does it mask company names on a CV?

Previous employers are not personal data and stay, so the AI can compare experience. You can add them to the mask with an organisation rule.

Does it work with payroll tables from Excel?

Paste the cells as text or export to CSV. Names, tax ids, ΑΜΚΑ and IBANs are recognised column by column, the amounts stay.

Can the DPO see what left?

Yes. A DPO role with read-only access to the organisation’s reports and the audit trail, without access to the real values.

Try it on a CV

Free account, no card. See what it finds before anything leaves.

Start free