Thalius

One question compared across every paper, report and filing

For research and regulatory teams. Hippocampus compares what every document says and gives each claim its own page. The cost per question stays low, because the model never reads the whole collection.

Analyse

Hippocampus

Compare the primary endpoints across the three approvals, with the page for each.

Approval AChange from baseline in the main scoreReview A, p. 31

Approval BTime to first eventReview B, p. 12

Approval CShare of patients who respondReview C, p. 8

What will next year's label update say?

The documents do not cover this.

Sources
Review Ap. 31
Review Bp. 12
Review Cp. 8

What it does

Three steps from question to answer

  1. Drawing of documents being added

    Add the whole collection

    Your papers, reports, reviews and filings. Add the new version when one changes.

  2. Drawing of a question typed into a computer window

    Ask one question

    In your own words. Hippocampus compares what every document says.

  3. Drawing of an answer with its source page

    Get each claim with its own page

    The answer draws on many documents, and each claim links to the full document and the page.

If your documents do not cover it, it says so. It does not guess.

The problem

What goes wrong today

Drawing of an old printed routine on a wall
01

Ten documents, every week

Your analyst reads ten documents to answer one question, then does it again next week.

Drawing of many PDF files in a search result
02

Confident, with no page

A chat assistant answers with confidence and no page reference. You check each claim by hand.

Drawing of a tall stack of documents
03

Split across documents

The answer sits in a table in one document and a footnote in another.

What you can count on

Drawing of your own documents

Answers from your own documents

From your papers, reports and filings. Not from the internet and not from guesses.

Drawing of an answer pointing to a page

Each claim shows its page

Each answer lists the document, the section and the page, so you can check each claim.

Drawing of an answer that says it does not know

Says so when it does not know

If your documents do not cover the question, it tells you. No answer is better than a wrong one.

Drawing of one question sweeping across a whole collection of documents

Works across the whole collection

One question draws on every document you have added.

Why it stays low cost

Low cost, also on a large collection

Drawing of an answer pointing to a page

For team leads

One place to update a document

Add the new version of a document and every answer after that uses it.

Drawing of a routine updated in one place

Customer story

Atrogi

Atrogi is a pharmaceutical research company. Its team asks Hippocampus questions across FDA reviews and labels: 10 documents, 2,198 pages. With Claude Opus 5 writing the answers, Hippocampus found the right passages for every question and got 93 of 96 answers right. It declined the one question the documents cannot answer, six times out of six.

  • 97% of answers correct across 2,198 pages of FDA documents

93 of 96 answers correct with Claude Opus 5 writing the answers, on Atrogi's question set. Three answers missed. We did not run other systems with Opus 5.

Fits your setup

Models fail as volume grows. Hippocampus makes it scalable.

Ask a model about a few pages and it does well. Ask it across thousands and its answers get worse. Hippocampus keeps the model on the right pages, so it stays accurate as the collection grows.

Your sources

Connects to SharePoint, Google Drive and Box.

Your files

PDF, Word, PowerPoint, Excel and scanned pages.

Your hosting

EU-hosted by default, or in your own cloud or on your own servers.

Your access

You set who sees what by role or function.

Hippocampus One memory of your documents

Your model

You choose the model per workspace and can change it without importing again.

Pick another model. The memory stays as it is.

Questions

Frequently asked

How many documents can it hold?

Starter keeps 25,000 pages. Corporate is sized to your collection.

How does it keep the cost per question low?

Hippocampus reads each document once and builds a memory of sections with summaries, and a question searches that memory without a generative model. Only the passages that answer the question go to the model, which leaves room for the strongest model on the hardest questions.

Can I check each claim?

Yes. Each answer lists the document, the section, the page range and the text it used.

What happens if our documents do not cover the question?

Hippocampus says the documents do not cover it. It does not guess.

How is this different from uploading files to ChatGPT?

On the FDA set, OpenAI File Search got 75.0% right and Hippocampus 83.3%, with the same model answering. On FinanceBench the gap is 52.3% against 92.2%.

Import your whole collection and ask the question you have not had time to answer.