Security & data handling

How uploaded PDFs are used

When you upload a reference PDF or enter a claim, RefCheckr extracts the relevant text, compares it against your claims, and locates supporting or conflicting passages. That is the full extent of how your content is used.

Documents and claims are not repurposed, indexed, or fed into any model training pipeline.

Storage

Uploaded PDFs are stored temporarily so that RefCheckr can generate your annotated output. Files are not retained beyond what is needed to complete the task, and can be deleted by the user.

Verification history is saved to your account so you can return to previous results, but the original PDF files themselves are not kept long-term.

AI models

RefCheckr uses AI models to analyse claims, search the literature, and identify relevant passages within your references. These models process your input at the time of the request and do not retain or learn from the content you submit.

Your documents are not added to any training dataset.

Confidentiality

RefCheckr is designed for use with the types of documents common in medical communications — manuscripts, CSRs, regulatory references, and similar materials. Uploaded references and claims remain private to your account or workspace and are not visible to other users.

Data location

RefCheckr's backend infrastructure runs on Railway, with data stored in a PostgreSQL database managed by the same provider. For specific questions about hosting regions or data residency, please get in touch.