Company Brain

Data protection in a brain

Every brain has its own data protection level (Open, Pseudonymise or Strict), independent of the workspace's protection level.

In a chat, an IBAN is often a mistake; in a brain it can be the answer. That is why every brain decides for itself what a model gets to see from its documents.

The level sits on the Settings tab at Personal data and is saved immediately. The person who created the brain and admins with access can make it stricter. Only workspace admins can loosen it.

A brain’s “Personal data” setting with the three levels “Open” (selected), “Pseudonymise” and “Strict”, each with its explanation.

The three levels

OpenPseudonymiseStrict
Passages in chatas storedwith placeholders, put back in the answerlike Pseudonymise
Title, summary, overviewfrom the original textfrom the pseudonymised textfrom the pseudonymised text
When adding documentseverything is acceptedeverything is accepteddocuments with an AHV, tax ID or social security number, IBAN, card number or UID/VAT number are refused
Images and scansare readare not readare not read

Pseudonymise replaces whatever the workspace's protection level pseudonymises (Data protection). With the workspace on Off or Standard, these are the six hard identifiers; names stay readable. Only with Strict, or a matching choice under Custom, are names, addresses and contact details replaced too.

What always applies

  • The real text is stored. Anyone with access sees the original values in the preview.
  • The search index uses the original values, so a question about a name finds something. A model at AWS in Zurich does this; it produces search values only, no text.
  • Workspace on Strict: nobody can set a brain to Open. A new brain starts on Strict there.
  • Security mode: there too, passages from a brain follow the brain's own level (Security mode).
  • Edit in chat: a document you edit in chat is a file of that chat there; the workspace's protection level applies.

No detection is perfect. How pseudonymisation works explains the method and its limits.

Changing the level

  • When you switch to Strict, Custodos checks the existing documents. If some contain hard identifiers, the dialog "Documents with sensitive identifiers in this brain" names them and you choose Remove and switch or Keep anyway and switch. Kept documents still reach the model.
  • For chats, the new level applies from the next message. Every change is recorded in the activity log.
  • After switching away from Open, images and scans not yet read are no longer read.

Which level fits

BrainLevel
Handbook with internal rules, scans and imagesOpen
A client mandate's correspondence with account and AHV numbersPseudonymise
Templates that should never contain account or AHV numbersStrict

Frequently asked questions

Next steps

On this page