AI at work,
with the people in view.
Custodian shows how AI assistants affect the people who use them.
Nobody gets to read the chats. Not even us.
Works with ChatGPT, Claude, Gemini and Microsoft Copilot, and with Claude Code, Codex and Copilot CLI
Nothing is captured until the employee switches it on
Capture can be paused at any time, and any chat can be excluded before it is sent.
Names and numbers are removed before storage
Records are kept under an anonymous ID, never under a username.
The analysis runs on your own hardware
One machine, an open model, no external AI service. Conversations can stay inside your network.
Six things it shows, nothing it should not.
A model built on Apertus, the open model of the Swiss AI Initiative, reads the de-identified text. It does not generate anything, and it does not diagnose.
The states of each message The five most likely of 166 mental states.
Trends for the person Strain, clarity, engagement and confidence, week by week.
Where the conversation is heading The five most likely states of the next turn.
A safety check on the assistant Finds 84% of the harmful replies in our held-out test.
Personal data removed before storage Names, emails, numbers, addresses, links and places.
Group figures for HR Never a name, an account, a conversation or one person's result.
Each person owns their results
The rules are built into the service, not written in a policy. A figure that would show one person is not computed.
How data is protectedThe participant
Their own states, trends and safety figures. They can download everything, or erase the account and all its records, without asking anyone.
HR at the organisation
Figures combined over five or more participants: averages, weekly trends, shared states. Never a name, an account, a conversation or one person's result.
The Custodian administrator
Participation counts under anonymous IDs. No conversation text, no individual results.
From a chat window to a private dashboard, in four steps
Capture, on the employee's terms
A browser extension records chats on four assistant sites, only while capture is on. The text waits in the browser until it is sent.
De-identification on arrival
Before anything is written to disk, names, emails, phone numbers, addresses, card and ID numbers, links and places are replaced.
Analysis on one machine
The model ranks the states of each message, predicts the next turn and rates each assistant reply. Nothing leaves the service.
Results for the person they belong to
Each participant reads their own dashboard. HR reads group figures. The administrator reads counts.
Numbers from conversations the model never saw
800 held-out conversations. The reference labels come from an automated annotator, so a score is agreement with that annotator, and the annotator agrees with itself at about 0.67.
How to read these numbersAI changes how people work before anyone measures it
Fifty messages, your own dashboard, no card
Create a free account, install the extension or the connector, and talk to your assistants as usual. After 50 messages, 25 of yours and 25 replies, the trial stops and your dashboard shows what Custodian saw.
- The same de-identification and the same model as a paid plan
- Only you see the result; nothing is shared with anyone
- Erase the account and everything with it whenever you like
- No email address asked, no card, no sales call
See what the signals look like across your organisation
Custodian starts with one team and grows from there. Each person joins by their own choice, and each one can leave at any time.