Sanaf AI
Start free
AI Document Extraction

PDF Vector, worked by an AI employee

Not another app for your team to learn, and not a set of rules for you to build. You hire an AI employee, you give it access to your PDF Vector account, and you ask it for things in Slack or Teams the way you would ask anyone else on the team. There is nothing to map and nothing to maintain.

  • AI Document Extraction
  • Connects with a key
  • 10 ready-made tools
  • Asked in Slack or Teams
At work

An illustration of how the conversation reads, not a transcript from a client account.

What PDF Vector is

PDF Vector parses documents into markdown, extracts structured data, answers document questions, and searches academic publications and grants.

You paste in a key from your own PDF Vector account. It is kept encrypted, and you can withdraw it from inside PDF Vector whenever you like.

How a run works

One message in, the work done in PDF Vector.

  1. 01

    You ask

    You message your AI employee in the chat your team already has open, in one sentence, in your own words.

  2. 02

    It works out the step

    It decides what the job needs in PDF Vector. You do not pick anything from a menu or wire anything together.

  3. 03

    It does the work

    Signed in to your own PDF Vector account, inside the access you granted it, doing the thing you asked for.

  4. 04

    It reports back

    It tells you what it did, in the same thread. If it could not do something, it says so rather than guessing.

10 tools it already has

What it can do in PDF Vector

These are the ready-made tools your AI employee already has in PDF Vector. It is not limited to them, but it never has to be taught these.

  • Ask DocumentAnswer one question from a general, identity, invoice, or bank-statement document. Processing consumes credits; the response reports the actual model and credit cost. The tool neve
  • Extract Document DataExtract schema-constrained structured data from a general, identity, invoice, or bank-statement document. Processing consumes credits and never retries with a higher model automati
  • Fetch PublicationsResolve up to 100 publication identifiers with provider auto-detection and return both resolved records and per-identifier errors.
  • Find CitationsFind relevant academic citations for each sentence in a paragraph and preserve provider-specific partial errors.
  • Find Similar PapersFind papers related to a seed publication using citation-network similarity, optionally including relationship edges.
  • Get Paper GraphRetrieve a publication plus one independently offset-controlled page of citing papers and one page of referenced papers.
  • Parse Academic PaperResolve an academic identifier or provider URL to a public PDF and parse it to markdown. Processing consumes credits, returns the actual model and credit cost, and never retries wi
  • Parse DocumentConvert a general, identity, invoice, or bank-statement document to markdown. Processing consumes credits; returns the actual model and credit cost and never retries with a higher
  • Search PublicationsSearch academic publications across selected databases and return one offset-controlled page, including any provider-specific partial errors.
  • Search Research GrantsSearch US, EU, and UK research-grant providers and return one explicit offset-controlled page with partial provider errors.
Access, and who is in charge of it

You stay the boss of your PDF Vector account.

Nothing connects until you approve it. You grant access one app at a time, you can take it back the same way, and everything your AI employee does in there is written down where you can see it.

How we handle your data
  • It signs in to your own PDF Vector account. You are not moving anything into ours.
  • You grant access one app at a time, and you can take it back the same way.
  • Everything it does in PDF Vector is written down, with what it did and when.
  • Anything you tell it to check with you first, it checks with you first.
Other apps in the same corner of the business

It works in PDF Vector and the rest of your software in the same job

A real job rarely stays in one place. Reading a message in one app, checking a record in another and writing the result in a third is one request to your AI employee, not three.

See every app

Questions people ask about PDF Vector

Can an AI employee really work inside PDF Vector?
Yes. It signs in to your own PDF Vector account and works in it the way a new hire would, from the chat your team already has open. Nobody installs anything, and nobody learns a new screen.
Do I have to move anything out of PDF Vector?
No. Nothing moves and nothing is replaced. Your records stay in PDF Vector, your team carries on in the same screens they used yesterday, and your AI employee works alongside them in there.
How does it get into my PDF Vector account?
You paste in a key from your own PDF Vector account. It is kept encrypted, and you can withdraw it from inside PDF Vector whenever you like. You approve it before anything connects, and you can take the access back the same way you gave it.
What can it actually do in PDF Vector?
It has 10 ready-made tools in PDF Vector today, among them Ask Document, Extract Document Data and Fetch Publications. The full list is on this page. It is not limited to those, but it never has to be taught them.
Can it use PDF Vector and the rest of my software in the same job?
Yes, and that is usually the point. Reading a message in one app, checking a record in PDF Vector and writing the result somewhere else is one request to your AI employee, not three separate ones you stitch together.
Who decides what it is allowed to do in PDF Vector?
You do. You grant access one app at a time and can withdraw it at any time, anything you ask it to check with you first it checks with you first, and everything it does in PDF Vector is written down with what it did and when.