This Privacy Policy explains how the Sift mobile application (the "App", "we", "us") collects, uses, and shares information when you use it. Sift lets you import your own documents (PDF and EPUB) and read them as AI-condensed summaries. We designed the App to keep your library on your device and to collect as little personal information as possible.
The short version
- The App has no account and no login. We never ask for your name, email, or contacts.
- The documents you add and your reading data are stored on your device.
- To create a condensed summary, the text of the document you are reading is sent to our secure processing service and to OpenAI, then the result is returned to you. We don't use it for anything else.
- We collect anonymous crash and diagnostic data to keep the App stable, and subscription status to unlock paid features.
- We do not sell your data, show ads, or track you across other apps or websites.
1. Who is responsible for your data
The App is provided by Khueon Studios ("the Developer"), which acts as the data controller. You can contact us at any time at [email protected].
2. Information we collect
2.1 Content you provide
- Documents you import. When you add a PDF or EPUB, the file and the text extracted from it are stored locally on your device so you can build a library and read offline. We do not upload or keep copies of your files on our servers.
- Text sent for condensation. When you open a document in condensed mode or gather ideas, the extracted text of that document (or the relevant sections) is transmitted to our processing service so an AI model can generate the summary. See Section 4 for details.
- Your reading data. Your reading position, chosen depth, saved ideas, and settings are stored on your device.
2.2 Information collected automatically
- Anonymous identifier. The App signs in to our backend using Firebase Anonymous Authentication. This assigns a random identifier to your installation so our servers can accept requests and prevent abuse. It is not linked to your real-world identity and contains no name or email.
- Crash and diagnostic data. Through Firebase Crashlytics we collect crash reports and basic diagnostics (for example device model, operating system version, app version, and the technical state at the time of a crash) to fix bugs and improve stability.
- Technical data. When your device contacts our backend, standard technical information such as IP address and timestamps may be processed transiently by our infrastructure providers to route and secure the request.
2.3 Purchase information
- Subscription status. Purchases are made through the Apple App Store or Google Play and managed via RevenueCat. We receive your subscription status (active, expired, plan, renewal date) tied to the anonymous identifier and your store account. We never receive or store your full payment card details — those are handled by Apple or Google.
2.4 What we do not collect
We do not collect your name, email address, phone number, contacts, photos, precise location, or advertising identifier, and we do not track you across other apps or websites. The App contains no advertising.
3. How we use information
- To provide the core features: importing documents, generating condensed summaries, and gathering ideas.
- To unlock and manage paid ("Pro") features and verify your subscription.
- To keep the service secure and prevent abuse of our processing service.
- To diagnose crashes and improve performance and reliability.
4. How your content is processed by AI
This is the most important thing to understand about the App:
- When you request a condensed read or idea gathering, the extracted text is sent over an encrypted connection to our backend (Google Cloud Functions) and then to OpenAI, which generates the condensed text or ideas. The result is returned to your device and stored locally.
- We send only the document text needed to produce the summary. We do not attach your name or contact details, because we do not have them.
- According to OpenAI's API policies, content submitted through their API is not used to train their modelsand is retained only transiently for abuse monitoring before deletion. Their handling is governed by OpenAI's privacy policy.
- On-device OCR. If a page is scanned or has no readable text, text recognition runs entirely on your device using Google ML Kit. The page image used for recognition never leaves your device.
5. Legal bases for processing (EEA/UK users)
Where the EU/UK GDPR applies, we rely on the following legal bases:
- Performance of a contract — to deliver the features you request, including AI condensation and subscription management.
- Legitimate interests — to secure the service, prevent abuse, and improve stability, balanced against your rights.
- Consent — where required by law; you may withdraw it at any time by discontinuing use of the relevant feature.
6. How we share information
We do not sell your personal information. We share information only with the service providers ("sub-processors") that make the App work:
| Provider | Purpose | Data involved |
|---|---|---|
| Google Firebase (Google LLC) | Backend functions, anonymous authentication, crash reporting | Document text (transiently, for processing), anonymous ID, crash/diagnostic data, IP |
| OpenAI, L.L.C. | Generating condensed summaries and ideas | Document text you choose to condense |
| RevenueCat, Inc. | Subscription management | Anonymous ID, purchase/subscription status |
| Apple / Google | Payment processing and app distribution | Purchase transactions (handled by the stores) |
We may also disclose information if required by law, to protect our rights, or in connection with a business transfer, in each case consistent with this policy.
7. Data retention
- On your device: your library, summaries, saved ideas, and settings remain until you delete them in the App or uninstall it.
- AI processing: document text sent for condensation is processed transiently to produce your result; it is not stored in a user profile by us.
- Crash data: retained by Firebase Crashlytics for a limited period (generally up to 90 days) and then deleted.
- Purchase records: retained by RevenueCat and the app stores for as long as needed to manage your subscription and meet legal/financial obligations.
8. Security
Data is transmitted over encrypted (HTTPS/TLS) connections, and access to our processing service requires an authenticated app session. No method of transmission or storage is completely secure, but we take reasonable measures to protect your information.
9. Your rights and choices
Depending on where you live, you may have rights to access, correct, delete, or restrict the processing of your personal information, to object to processing, and to data portability. Because the App has no account and stores your content on your device:
- You can delete all your on-device data at any time by deleting content in the App or uninstalling it.
- To make a request regarding data held by our providers (for example crash data or subscription records associated with your anonymous identifier), email [email protected]. We may need information to locate the relevant records.
California (CCPA/CPRA):we do not sell or "share" personal information as those terms are defined, and we do not use it for cross-context behavioral advertising. You may exercise applicable rights using the contact above; we will not discriminate against you for doing so.
10. International data transfers
Our providers are located in the United States and may process data there and in other countries. Where required, these transfers are covered by appropriate safeguards such as the European Commission's Standard Contractual Clauses.
11. Children's privacy
The App is not directed to children under 13 (or under the minimum age of digital consent in your country), and we do not knowingly collect personal information from them. If you believe a child has provided us information, contact us and we will delete it.
12. Changes to this policy
We may update this Privacy Policy from time to time. When we do, we will revise the "Last updated" date above and, where appropriate, provide additional notice within the App. Your continued use of the App after an update means you accept the revised policy.
13. Contact us
If you have any questions about this policy or your data, contact us at [email protected] (Khueon Studios).