PrivaSearch
Book a demo

How PrivaSearch works

Pseudonymise and check first. Only then AI.

PrivaSearch sits between your documents and the AI model. Personal data is detected within PrivaSearch itself and replaced by consistent pseudonyms; a person approves before anything becomes searchable.

PrivaSearch is software that lets your team search its own client files with Claude, ChatGPT or Mistral Vibe, after names, BSNs (Dutch citizen service numbers) and addresses have been replaced by pseudonyms and a colleague has checked that.

Book a demo
  • A person approves every document
  • SharePoint stays read-only
  • One price for your whole firm
A minute and a half: what happens when a client file lands in a chat window, and how PrivaSearch answers the same question: detection, pseudonymisation, human review, search with source references and connecting through MCP.

Step by step

From upload to answer in five steps.

01

Collect

Upload files or connect a SharePoint library. Read-only: nothing changes in your source systems.

The screen where you choose folders from a SharePoint library, each of which becomes a project

02

Detect

A language model within PrivaSearch and Dutch patterns find names, addresses, BSNs (Dutch citizen service numbers), IBANs, Dutch number plates and dates of birth. No outside AI provider looks on at this step.

The detected personal data by type, with the original next to it

03

Review

A colleague sees the original and the pseudonymised text side by side, corrects what the model missed and explicitly approves.

The privacy review: the original with highlighted personal data and the list of detections

04

Search

Questions such as "what is the notice period?" are answered with passages and source references, per project, only for those who have access.

Search results: pseudonymised passages with a reference to document and page

05

Connect

Claude, ChatGPT Business or Mistral Vibe searches the same released passages through a secure MCP connection. Never the originals.

The consent screen where you give an AI assistant access to released passages

Limits of the model

What the AI does and doesn't see.

  • Does: released, pseudonymised passagesLimited in size, with a page reference, only from projects the user is a member of.
  • Doesn't: original files, file names or linksThe AI gets no access to your storage. In the standard configuration the AI layer has no route to the original.
  • Doesn't: who is behind a pseudonymThe link between pseudonym and person sits in a separate vault, with a key per organisation. Revealing is only possible in PrivaSearch, with a permission check and a log entry.
  • Search queries are filtered tooIf someone accidentally types a name into the PrivaSearch search field, it is replaced before the question reaches the model.
  • Does: what you type into a connected assistant yourselfIf you ask the question in your AI assistant instead of in PrivaSearch, that question goes straight to the provider of that assistant — bypassing our pseudonymisation. So don't put names in it, and only connect business accounts with a data processing agreement. How MCP and the GDPR fit together.

Access

Permissions follow your organisation.

  • Per organisation, per projectEvery organisation has its own database and its own address. Within the organisation, project membership determines who sees what; administrators get no automatic access.
  • SharePoint stays in chargeWith every request there is a live check whether the user may still see the document in SharePoint: when searching, when viewing, when downloading and through the MCP connection. Permissions revoked? Then it's gone here too.
  • Two-step verification and device confirmationMandatory for everyone. New devices are confirmed with a code by email.
  • Retention periods with teethAn end date per project. After that, access is blocked and copies, fragments and pseudonyms are cleaned up, unless a legal hold applies.

No training, no access

Everyone who searches knows what they're working with.

Employees take a short AI literacy training (in line with Art. 4 of the EU AI Act) with periodic refreshers. Without a valid training the workspace doesn't open and the MCP connection refuses too.

Frequently asked questions

What you want to know about how it works.

What is PrivaSearch?

PrivaSearch is software that lets your team search its own client files with Claude, ChatGPT or Mistral Vibe, after names, BSNs (Dutch citizen service numbers) and addresses have been replaced by pseudonyms and a colleague has checked that.

Which personal data does PrivaSearch detect?

A language model within PrivaSearch and Dutch patterns find names, addresses, BSNs (Dutch citizen service numbers), IBANs, Dutch number plates and dates of birth. No outside AI provider looks on at this step.

Who checks the documents?

A colleague. Automatic detection is never complete. That is why the human review is mandatory and PrivaSearch always shows the original next to the pseudonymised text. A colleague corrects and explicitly approves; only then does a document become searchable.

Does the AI see my original files?

No. Your AI assistant only gets released, pseudonymised passages, with a page reference and only from projects the user is a member of. It doesn't see original files, file names or links, nor who is behind a pseudonym.

Which AI assistants does it work with?

You connect Claude, ChatGPT Business or Mistral Vibe through a secure MCP connection. You can also search entirely within PrivaSearch itself: the connection is an extra, not a requirement.

What happens to what I type into my AI assistant myself?

If you ask the question in your AI assistant instead of in PrivaSearch, that question goes straight to the provider of that assistant — bypassing our pseudonymisation. So don't put names in it, and only connect business accounts with a data processing agreement.

What does it cost?

One price per organisation a month, not per user: €175 for up to 15 employees, €350 for up to 30, excl. VAT. Above that, on request.

Updated on

See in twenty minutes what happens to your documents.

We show it with fictitious client files from your sector: upload, detection, review, search and the connection with your AI assistant. Afterwards you'll know exactly what your team can use safely.

Book a demo →