Document pseudonymisation for AI

Your teams use ChatGPT and Claude on client files. Safe-Doc makes it safe.

Pseudonymise sensitive documents before AI. Restore the output after. Nothing stays with us. Ever.

Banning AI doesn't work : your teams already use it. Routing everything through a closed platform means storing your files with a third party and handing over your prompts. Safe-Doc supports the usage that already exists: your tools, your habits : protected the moment a document leaves. Nothing is kept.

Before John Smith · £14,500 · j.smith@corp-partner.com

After [PERSON_01] · [AMOUNT_01] · [EMAIL_01]

55+
sensitive data types detected
6
countries covered
0
documents stored
Any
AI tool, your choice

Try Safe-Doc for 14 days.

Full product access, no credit card. Pseudonymize real documents and use any AI tool.

Banning AI doesn't work : it's already here.

Your teams already paste confidential documents into ChatGPT. Figures below come from our Shadow AI page : cited sources, not extrapolated.

80%
of employees use unapproved AI tools
27.4%
of data copied into AI tools is sensitive
46%
would continue even after an explicit ban

Sources: IBM, Cyberhaven, Software AG : details on AI Risks

A security layer, not another platform.

A security layer, not another platform. "Workspace + integrated chat" platforms store your files and see your prompts: versions, history and mapping tables pile up with a third party. Safe-Doc processes, restores, and hands control back. Your file never becomes an archive on our side.

The group project takes months. AI usage is already here.

Safe-Doc doesn't wait for your enterprise platform: it's the layer that secures existing usage during the transition : no lock-in, no conflict with the roadmap ahead.

Keep your tools. Add the safety.

Tool freedom

Any AI: ChatGPT, Claude, Gemini, Copilot. No lock-in, no quota. Your subscription stays yours, and it's always the best model available.

Workflow freedom

No workflow change, no training. Protection is added; your teams change nothing. That's what makes it adopted instead of bypassed.

Vendor freedom

Zero storage. Nothing stays with us: nothing to audit elsewhere, nothing to retrieve if you leave, no lock-in.

ChatGPT Claude Gemini Copilot Mistral

Keep your AI and your subscription. No lock-in, no quota.

People collaborating around a laptop
Same tools, same habits — with a safety layer added before AI.

Speed, cost, always the best AI.

Speed

Live in minutes. No migration, no platform to learn, no hardware requirement.

Cost that follows adoption

Start at €35, grow in seats and pages at the real pace of usage. No upfront platform commitment to justify before proving value.

Always the best AI

A dedicated AI is frozen on one model; the frontier moves every quarter. Safe-Doc stays a model-agnostic layer: always plug in the best model, today and tomorrow.

The same truth, for your role.

Pseudonymise → analyse → restore.

Same AI tools. Web UI, API or MCP. No sensitive data leaves your control.

01
Pseudonymise

55+ entity types replaced with neutral tokens. Metadata wiped. Single document or Data Room batch with consistent pseudonyms.

02
Use any AI tool

Copy-paste, call via API, or connect through MCP — into ChatGPT, Claude, Gemini or Copilot, your choice. Safe-Doc never sees your query. No integrated chat. No lock-in.

03
Restore

Re-inject original data into the AI output via encrypted mapping. Locally. Auditable. Under your control only.

Built for anyone handling sensitive documents.

Not just lawyers. Any professional team that uses AI on confidential content.

Zero storage by design.

Nothing stays with us.

Your documents are never stored on Safe-Doc servers after processing. The pseudonymised version goes from your browser directly to the AI tool of your choice. Safe-Doc never sees your query.

Unlike "workspace + integrated chat" platforms where every question transits through their servers, Safe-Doc processes and purges. The mapping (reversible mode) is encrypted, TTL-controlled, and under your sole control, not a centralised archive on our side.

Control & purge

Temporary processing. No document content retained in logs or database after treatment.

Confidentiality

Encryption in transit. Only the pseudonymised content reaches the AI of your choice.

Auditability

Operation logs and residual risk indicators included in every export report.

One plan for every team size.

Solo
35€ /month
  • 1 seat
  • 1,200 pages / month
  • Full pseudonymisation
  • Metadata wipe
  • Data Room
  • JSON mapping (reversible)
Cabinet+
399€ /month
  • 10 seats
  • 20,000 pages / month
  • Everything in Cabinet
  • +35€ per extra seat
Get started
Enterprise
Custom
  • Unlimited seats
  • Unlimited pages
  • SSO
  • Audit logs
  • Dedicated infrastructure
  • DPA & SLA
Contact us
Add-ons:
  • Page pack: +35€ / 1,500 pages (all plans)
  • Extra seat: +35€ / seat (Cabinet and Cabinet+ only)

You or your teams already use AI on confidential documents : with or without your approval.
That's Shadow AI.
We don't ban AI. We make it safe. GDPR art. 4(5) pseudonymisation : a recognised security measure, not a substitute for your governance.

Understand Shadow AI