Step 1, upload
You open Continuum and drag your files in. PDF, JPG, and PNG are accepted, up to ten files at a time, each no larger than 15 MB. Every file shows up in a list, and you can remove any of them before you submit.
A checkbox confirms that you understand this is not medical advice and that your files will be deleted right after processing.
Optionally, you can also tell Continuum how you feel here. It asks a few plain questions the way a doctor would, when a symptom started, what the pain feels like, whether anything travels with it, and maps your answers onto a simple body outline. It is optional, you can skip it at any time, and it organises your symptoms without ever diagnosing.
Step 2, read and organise
Continuum sends your documents to a language model trained to read medical content. In three passes we extract what is there:
- Facts: medications with dose, diagnoses your clinicians explicitly named, lab values, dates, allergies.
- Timeline: a chronological list of medical events, neutrally phrased.
- Brief: a coherent one-page summary, plus three questions you might raise.
We actively prohibit the model from speculating. If a value is unclear, we omit it. If the model itself is uncertain, we flag that at the top of the brief.
At this moment we delete your original files. There is no step in which we keep them.
Step 3, the PDF
You receive an A4 PDF. It looks like a doctor letter. Six sections: patient snapshot, active medications, timeline, recent changes, open items, notes for your doctor. Printable, shareable with family, archivable.
If you have an account, you can save the brief, give it a title, and share it with a family member. Otherwise it lives at a random link for one hour and then disappears.
What does not happen
- We do not sell your data or use it for advertising.
- We do not train models on your documents. Anthropic, our AI provider, is contractually bound not to do the same.
- We do not diagnose, recommend treatment, or use alarming language.