How do you keep your AI questions private?
Turn on Privacy Shield before asking a sensitive question. On a supported text flow, it detects and replaces identifiers like names, contact details and reference numbers with placeholders before the question reaches a model, then restores them in the answer you read. It's opt-in, detection is automated so it can miss unusual identifiers, and it doesn't cover images, attachments or every tool.
Free · iOS & Web · Privacy Shield on every plan
Why does AI privacy matter?
The questions worth cross-checking are often the most personal — a symptom, a contract, a financial situation. Sending those to AI in the clear means handing personal data to third-party services. Reducing what you disclose before you ask keeps the usefulness while lowering that exposure.
What does GDPR-friendly AI mean here?
It means data minimisation by design: when you enable Privacy Shield on a supported text flow, the model receives the question with detected personal identifiers replaced. It reduces what's submitted; it doesn't replace your organization's own rules on what may go to a third-party processor, and it can't remove context that identifies someone indirectly.
How does Satcove's Privacy Shield work?
On a supported text flow, Privacy Shield detects common identifiers — names, contact details, reference numbers — and replaces them with placeholders before the question reaches the models. The placeholders are restored locally, where supported, in the result you see. It's an opt-in setting, not a default, and it currently covers supported text flows — not images, attachments, or every tool.
FAQ
What is private AI?
AI where you can reduce what you disclose before asking. With Privacy Shield on for a supported text flow, detected identifiers are replaced with placeholders before the question reaches a model, and restored in the answer you read.
Is Satcove GDPR-friendly?
Privacy Shield adds data minimisation before supported model calls, replacing detected personal identifiers. It reduces direct identifiers submitted; it doesn't replace your own organization's rules or a provider's privacy terms.
How does Privacy Shield work?
When enabled on a supported text flow, it detects personal details in your question, replaces them with placeholders before the models see anything, then restores them locally where supported. Detection is automated and can miss unusual or contextual identifiers.
Does it cover images or every Satcove tool?
No. Privacy Shield currently covers supported text flows. Images, attachments and some tools may need separate handling — avoid including sensitive details that aren't needed for the request.
Is it available for free?
Yes. Privacy Shield is available at no extra cost on all plans, including Free, on iPhone and the web — no card required to start.
Keep exploring
Satcove
Free · iOS & Web · Privacy Shield on every plan