Coming soon

Anonymise your data before the ChatGPT, Claude or Gemini APIs

Your teams want to use the best models on the market, but those APIs send your data to third-party vendors. We are currently developing and testing an anonymisation layer that masks sensitive data before it is sent, then restores it when the answer comes back, so as to limit leaks while keeping the power of these models.

Status: coming soon, currently in the testing phase. The elements presented below describe the approach we are validating before opening it up in production.

The problem: every prompt is a potential leak

As soon as a user copies a document into ChatGPT, Claude or Gemini, the data leaves your perimeter: surname, first name, email address, IP address, case file number, health data and more. That information travels and can be retained by the vendor. For many organisations this is unacceptable, but banning these tools only pushes people towards shadow IT.

The approach we are testing: mask, send, restore

1

Detection of sensitive data

An engine automatically spots personal data in the text: names, emails, IP addresses, numbers, addresses and more.

2

Replacement with tokens

Each item of data is replaced by a neutral token. The meaning of the sentence is preserved, but no personal information leaves any more.

3

Sending to the third-party API

Only the anonymised text is transmitted to ChatGPT, Claude or Gemini. The mapping table stays with you.

4

Restoration on receipt

When the answer arrives, the tokens are replaced by the real values. The user receives a complete result; the vendor has never seen the real data.

The round trip, in one diagram

Only the masked text crosses the boundary. The mapping table, the only key for reading the real values, never leaves your infrastructure.

ON YOUR SIDE · your infrastructure THIRD-PARTY API Original text “Jean Dupont, case file no. 74123” ① masking Masked text “[PERSON_1], case file [REF_1]” Restoration tokens → real values → complete answer, in the clear Mapping table [PERSON_1] → Jean Dupont the key: never leaves Third-party API ChatGPT · Claude · Gemini ② sent: masked text only ③ answer (still masked)
The vendor only ever sees tokens; it never has access to the real data.

A concrete example

Original text (stays with you)

“Please get back to Jean Dupont at j.dupont@ville.fr about case file no. 74123.”

Sent to the API (anonymised)

“Please get back to [PERSON_1] at [EMAIL_1] about case file [REF_1].”

Restored answer (user side)

“A follow-up email has been drafted for Jean Dupont (j.dupont@ville.fr), case file no. 74123.”

Defence in depth, not a miracle cure

Anonymisation sharply reduces the exposure of personal data, but it does not replace a sovereign AI: detection is never 100 % perfect, and the channel is still that of a third-party vendor. It is an excellent complement when the use of external APIs is unavoidable.

For full control, the best answer remains sovereign AI hosted in house, where the question of leakage no longer arises.

Take part in the testing phase

This solution will be available soon (testing phase under way). Contact us to be told when it opens, or to take part in the trials with your own use cases.

Keep me informed