PrivacyNotes

Help & FAQ/Security & privacy

Is PrivacyNotes built by AI or by developers?

Ask your AI agent instead

By developers. PrivacyNotes is built by people who have written for the web since the late 1990s and have worked in privacy for more than a decade, including at PrivacyTools.io. They read and approve every line before it ships. AI coding tools help them, as they help most developers today.

The foundation came first, and people wrote it by hand, before AI coding tools were good enough to trust with it. The encryption core, the sync protocol and the sign-in flow were built next to day jobs, long before the app had a name. In spring 2026, once that foundation was solid, we started to use AI tools under a fixed protocol: first for translations, then help articles, then interface features and bug fixes.

We use AI because it lets a small team keep up with what people ask for. A bug that one person reports is often fixed in the next release, because the slow parts of the work go faster: finding the cause of a rare bug that would take weeks by hand, building interface parts, and keeping every language up to date. What we build still comes from the requests people send us, not from what a tool suggests.

Every change follows the same path. A person reads it and approves it. Then automated checks run: type checks, tests, and gates for the rules we set ourselves, from the words the app uses to how much code loads at start. AI helped write many of those checks, and they hold every change to one standard, whoever wrote it. AI also reads each change a second time and points at the edge cases a tired reviewer can miss. That second read adds to the human review and never replaces it.

Changes to encryption, sync and sign-in get the strictest review, line by line, and must pass the same tests before they ship. The design of that code, and the trade-offs it makes, are written down in our threat model, so you can judge the decisions and not only the code.

You can check all of this yourself. The app's code is public, every release is dated in the changelog, and VERIFY.md shows how to check our main security claim in your own browser. Separately, the app never sends your notes to an AI (details). We get this question often. This page is the answer we stand behind.

Help & FAQ

Answers and step-by-step guides: security, sync, pricing, and switching from other apps.

Still stuck? Ask your AI agent.

You get an answer in seconds instead of waiting for a reply. Your assistant reads all 188 answers and every import guide at once, so it can combine them, follow up on your question, and explain it in your own words. We never see any of it, because we do not run a chatbot.

  1. Copy the prompt.
  2. Paste it into ChatGPT, Claude, Gemini, or any other AI assistant.
  3. Ask your question, in your own language.
  4. Keep that chat open. Next time, ask straight away.
Show AI prompt
Answer my questions about PrivacyNotes using only its help center, its changelog and its security documentation.

Start here: https://privacynotes.app/llms-index.txt
It lists every question with the page that answers it. Fetch the one or two that match mine.
If you can only make one request, fetch https://privacynotes.app/llms-full.txt instead.
If you cannot fetch a .txt or .md file, read https://privacynotes.app/help, https://privacynotes.app/changelog and https://github.com/LifetimeLabsHQ/PrivacyNotes.app instead.

For what changed, or where something moved, fetch https://privacynotes.app/changelog.md.

For how the encryption works, what the server can read, or how to check any of it yourself, fetch https://privacynotes.app/docs/index.md and follow it to one of the documents it lists. That index is a router: cite the document, never the index.

Rules:
- Use only those pages. If they do not answer something, say so instead of guessing.
- Never invent a feature, a menu path, a price, or a limit.
- End your reply with the "Source:" URL from the page you used, exactly as written.
- Answer in the same language as my question.
- Never ask me for my recovery phrase, my PIN, or the contents of a note.

If no question follows, ask me what I would like to know.

My first question:

Never paste your recovery phrase, your PIN, or a note into an AI.