Give it the documents you already have — contracts, resumes, invoices, reports. It reads every one of them, lays them out so you can find and sort what you need, and answers your questions from them, showing you which document each answer came from.
| Supplier | Renews | Notice | Owner |
|---|---|---|---|
| Northwind Logistics | Sep 01 2026 | 60 days | Operations |
| Acme Cloud Services | Sep 30 2026 | 30 days | IT |
| Bluepeak Facilities | Sep 14 2026 | 90 days | Facilities |
No setup to learn and no jargon to get past. You hand over a set of documents, and from that moment on you can find them, sort them, and talk to them.
Drop in a whole folder of files, paste in text, point it at a website, or connect a source that keeps itself up to date. Any number of documents, mixed formats, all at once.
Every document becomes a row, and the details you care about become columns — so you can search, sort and filter your way to the exact documents you want instead of opening them one by one.
Ask a question the way you'd ask a colleague and get the answer out of your own documents — with the documents it read shown underneath, so you can check it yourself.
Your documents live in a collection — one set of documents that belong together, like every supplier contract or every applicant CV. Each collection is separate, with its own documents and its own details. Most people set one up in a couple of minutes.
You never have to take an answer on faith. Open the sources and you’ll see which documents were read, which parts of them were used, and the original wording — word for word.
Ask in plain language and get a proper answer — with tables and charts where they help. Each question and its answer stay together as one numbered exchange, so a long conversation never turns into a wall of text. Open the sources beneath any answer to see each document’s summary, its details, and the exact parts that were used. If something isn’t there, it says so rather than guessing.
Every document is a row and the details you chose are columns. Search, sort, filter on several rules at once, hide what you don't need, and export exactly what's on screen.
Pick any detail — supplier, document type, year — and see every value it takes with a count, then jump straight to the documents behind it.
Upload files, paste text, add a website, or connect a source that syncs on its own. New documents join the collection and the originals stay downloadable.
Documents still being read are labelled as such. Details that aren't there are said to be missing, not invented. Nothing is dressed up.
You pick one of these when you create a collection, and you can switch later. That’s the only fork in the whole product; everything else is decided for you.
Your documents become searchable and you can start a conversation with them right away. No details are pulled out, so there’s no table to sort — good when you only want answers.
The same conversation, plus the details you name are pulled out of every document — so answers can be exact and the whole set turns into a table you can sort, filter and export.
One collection never mixes with another. Contracts and CVs keep their own documents and their own details, so what you set up for one can’t spill into the other.
Every collection stands on its own — its own documents, its own details, its own conversations.
Download the file you uploaded, or the plain text read out of it, at any time.
Each collection carries an ID you can quote to support or use in your own systems.
Add a handful of them, ask your first question, and see where the answer came from.