CVs, disciplinary notes, exit interviews — the documents HR handles are exactly the ones that must never leak. You shouldn't have to anonymise a candidate pack by hand before pasting it into ChatGPT or Claude — and then de-anonymise the answer afterwards. That's what we do for you, automatically, before anything leaves your computer.
No card required. You land straight in a simple chat — drop a file and ask.
Three steps. No setup, no training, nothing to install. If you can attach a file to an email, you can use this.
Drag in the CV, interview notes, disciplinary report or survey export you're working on. Before anything leaves your computer, employee IDs, reference numbers, emails and phone numbers are swapped for neutral placeholders automatically. Candidate and employee names are caught by a name-detection model that runs on your device too — and if it isn't ready yet, the send is held rather than risk a name slipping through.
"Summarise these interview notes." "Compare these three CVs against the job spec." "Draft a neutral summary of this grievance file." The AI does its work seeing only the placeholders — never who the person actually is.
The reply comes back with the real names restored — automatically, exactly where they belong. No find-and-replace, no un-renaming, no copy-paste gymnastics. Just the finished answer.
We can't leak your people's data — we don't have it. The swap happens before your file leaves your machine, and we keep nothing afterwards: no copies of your documents, no copies of the answers. There is simply nothing on our side to breach, subpoena or lose.
Employee IDs, reference numbers and contact details are caught deterministically, every time. Free-form candidate and employee names use a small name-detection model that also runs on your device; recall is strong on common names but not perfect (unusual or non-Latin names can be missed). For your most confidential files, install the desktop app — it tokenises the file itself entirely on your own machine before anything is sent to the AI, keeps your API key and logs local, and stores tokens in an encrypted vault.
Employee and candidate data sits squarely under GDPR and employment-privacy law — and under something stricter still: your colleagues' trust. These are the guarantees that make AI compatible with both.
The workarounds people use today are slow — and fragile.
The manual rename. "Candidate A", "Employee X", find-and-replace before pasting — then reversing it all in the answer, hoping you didn't miss one instance on page 14.
The retyped summary. Typing an anonymised version of the document by hand because uploading the real one feels wrong. Half an hour gone before the AI has even started.
The quiet rule-break. Pasting the real thing and hoping it's fine. It's the fastest option — and the one that can cost someone their privacy — and the company a claim.
The blanket ban. The firm forbids AI entirely, and the productivity gain everyone else is getting goes to your competitors instead.
The duty of confidentiality isn't unique to HR. If people trust you with their private affairs, this is built for you too.
Plain answers, no fine print surprises.
The leading AI models — the same ones behind ChatGPT, Claude, Gemini and others. The difference is what they're allowed to see: with us in between, they get your question and a version of your document with all the identifying details replaced by placeholders. They do the thinking; they just never learn who it's about.
The swap list — which real name maps to which placeholder — is created on your device and used to restore the answer on the way back to you. It's applied automatically, so the document you download reads exactly as if the AI had seen the real names all along.
Every request comes with a signed, tamper-proof receipt: a small certificate recording when the request happened and that the protections were applied. You can verify it independently, months later, and keep it in the personnel file.
No. We keep no copies of your documents, your questions or the answers. Once your download completes, it exists only on your machine. That's the point: we can't leak what we don't have.
Yes — and the mechanics work in your favour: contact details and identifiers are swapped for placeholders automatically — and candidate names by an on-device model that holds the send until it's ready — before the AI sees anything, so the comparison it makes is between the contents of the documents, not the people on the letterhead. The real names come back in your download, and nothing about any candidate is stored anywhere along the way.
No. Create a free account and you land directly in a simple chat. Drop a file, ask your question — that's the whole workflow. Prefer to stay in the tools you already use? After you register, you can install a small browser add-on for Chrome or Firefox and keep using ChatGPT, Claude, Gemini or Grok as you do today — names, emails and account numbers are anonymised inside your browser before anything is sent, and the add-on downloads from your account page. (If your firm has an IT team that wants to connect it to internal systems, there's a full technical setup for them too, but you never need to touch it.)
Free to start, no card required. Drop a document, ask your question, and see the answer come back with the names where they belong.
Questions first? Write to hello@cloakapi.io — a human answers.