← CIRE

Privacy Policy

Last updated: 21 September 2026

1. Scope

This policy covers CIRE (the “Service”) at cire.patridex.com. CIRE is a research reading tool: you bring documents, and it derives concepts, definitions and maps from them. This policy describes what that requires us to hold about you, and what we do not do with it.

2. What we collect

  • Account identity. When you sign in, our authentication provider passes us your email address and, where your sign-in provider supplies them, your display name and avatar image URL. That is the whole of the account record.
  • Documents you upload. The file, its title, and a reference to where it is stored.
  • What CIRE derives from them. Concepts and keywords found in your documents, their definitions, paper context, domain graphs and idea trees, the snippets you save to your research ledger, and any ontologies you build.
  • Technical data. Ordinary server and request logs kept by our hosting provider, and a session cookie. We run no advertising or third-party analytics trackers.

We never hold a password for you. CIRE does not offer password sign-in: access is by emailed one-time code or by a third-party provider, so there is no password of yours for us to store or to lose.

3. How we use it

  • To operate the Service — signing you in, storing your documents, and generating and displaying the artifacts you asked for.
  • To keep the Service secure and working, including debugging and abuse prevention.
  • To contact you about the Service itself: security notices and material changes.

We do not sell your personal information, we do not share it with advertisers, and we do not build advertising or behavioural profiles from your documents.

4. AI processing of your documents

This is the part worth reading twice. To produce a definition, a map or a tree, CIRE sends the relevant excerpt of your document — and in some cases surrounding context from it — to a third-party large-language-model provider over an encrypted connection. That provider processes the text to return a result and acts as our processor in doing so. We do not use your documents or the artifacts derived from them to train models, and we use the provider under API terms that exclude submitted content from training its models by default.

If a document is confidential, embargoed, export-controlled, or covered by a data agreement that forbids third-party processing, do not upload it to CIRE.

5. Who else processes your data

We keep the list of sub-processors short and name all of them. Each is bound to process the data only to provide its service to us. All process data in the United States, so data from outside the US is transferred there.

  • WorkOS — authentication, and the record of your sign-in identity.
  • Vercel — application hosting, and the request logs that come with it.
  • Neon — the Postgres database holding your account, documents and artifacts.
  • OpenAI — large-language-model inference, as described in §4.

Beyond these, we disclose personal data only where the law requires it, and we will tell you about such a demand unless we are forbidden to.

6. Retention

Your documents, artifacts and account record are kept until you delete them or ask us to close your account, after which they are removed from the live database within 30 days and fall out of rolling backups thereafter. Server logs are kept on our hosting provider’s default schedule, which is measured in days, not years.

7. Your rights

Wherever you live, you may ask us to give you a copy of what we hold about you, correct it, delete it, export it, or stop or restrict a particular use of it. If you are in the UK, EU, or a US state with a comprehensive privacy law, those are statutory rights and you also have the right to complain to your data protection authority. We will not charge you for making a request or treat you differently for having made one.

See §10 for how to reach us while a dedicated address is being set up.

8. Security

Traffic is served over HTTPS with HSTS. Session cookies are set Secure, HttpOnly and SameSite, so they are not readable by page scripts and are not sent across sites. Sign-in uses the OAuth authorization-code flow with PKCE, and API routes reject unauthenticated requests rather than redirecting them. No system is perfectly secure, and we do not claim otherwise.

9. Age

CIRE is not directed to children under 13 and we do not knowingly collect their personal information. The minimum age to use CIRE is stated in the Terms of Service. If you believe a child under 13 has given us personal information, tell us and we will delete it.

10. Contact

CIRE does not yet have its own mail domain, and we would rather print no address than one that bounces. A dedicated privacy contact will be published here as soon as it exists. Until then, privacy requests can be made through whichever channel you used to get access to CIRE, and will be handled on exactly the terms set out above.

11. Changes

We will update this page when the Service changes what it does with your data, and move the date at the top. For a change that materially affects your rights we will tell account holders directly rather than relying on you to re-read this page.