Feature · Security · Written by Yobel Tzegai · Last checked 9 October 2026
Yes. One switch in Settings, under Data & privacy, stops every call to our AI provider, Anthropic, for your whole workspace. Only the workspace owner can change it, and every change is in the audit log. With it off, Complipath (complipath.io) searches your files on our own server, and drafts, suggestions and the assistant say they are turned off.
One switch in Settings stops every call to our AI provider, Anthropic, for the whole workspace.
Settings, then Data & privacy: Send data to our AI provider (Anthropic). It is on by default, and the table under it says what each feature sends at most. The full list of what reaches each party is on the subprocessors page.
€499 a month
Prices exclude VAT.
Only the workspace owner. Everyone else sees the switch and the line Only the workspace owner can change this. Turning it off or on writes a line in the workspace's audit log, with who did it and when, so a reviewer can see when AI processing was allowed and when it was not.
No. No language model is in the decision path: the risk class comes from the rule engine, with the article it rests on, whether the switch is on or off. AI only drafts, and a person confirms; what changes is the help around it. Drafts and suggestions stop, and files are searched by keywords on our server instead.
Nothing from your workspace while you are signed in: every call the app makes for a signed-in person goes through one place that reads the switch first. The public check before sign-up has no workspace to read, so its reading step is not covered, and Perplexity is not Anthropic.
Every plan, the free one included: the app lists it for every plan. Free holds one AI system, with no end date. Starter is €499 a month for up to 20 AI systems. Prices exclude VAT. Growth and Scale are not available yet, and nothing here waits for them.