PaperPaper
FeaturesReviewsHelpAbout
Log inGet Paper free

How it works

How Paper turns your sources
into a study partner.

Upload a PDF, a lecture recording, or a website. Paper indexes the content, then lets you chat with it and study it - with every answer tied back to a specific page or timestamp.

The pipeline

From upload to cited answer in four steps.

Paper is built on retrieval-augmented generation (RAG) - the pattern that lets an AI model answer questions about your own documents instead of guessing from its training data. It looks something like this:

  1. 01

    Upload a source

    PDF, audio, video, EPUB, Word, PowerPoint, web URL, YouTube link, or an import from Notion or Outline. Paper handles the extraction.

  2. 02

    Paper extracts the text

    Scanned PDFs run through OCR. Videos and audio are transcribed (with speaker labels). The full text is split into passages on natural boundaries - paragraphs, page breaks, timestamp groups.

  3. 03

    Each passage gets an embedding

    An embedding is a numerical fingerprint that captures the meaning of the passage. Passages with similar meaning end up close together in the index, even if they use different words.

  4. 04

    You ask a question. Paper finds the right passages.

    When you chat, Paper searches the index for the passages most relevant to your question, then asks an AI model to answer from that context, with citations back to the source. When source-only mode is enabled, the model is instructed to answer only from your selected sources.

Trust

Source-grounded answers cite their source.

Paper is designed to cite the page or timestamp behind its answers wherever the answer depends on your sources. You see something like [p. 5] or [3:42] beside each claim. Clicking it jumps you to the exact spot in the PDF viewer or the video player.

This is the simplest defence against hallucination: every important claim should be traceable to something real. If an answer seems off, you can open the citation and check the original source in one click.

Control

You decide what the AI sees.

Each chat sits on a page with one or more sources attached. You can:

  • Toggle individual sources on and off for any chat turn.
  • Narrow a PDF to a specific page range (e.g. only chapters 4 to 7).
  • Narrow a video or audio source to a specific timestamp window.

The AI only ever sees what's selected. Pages don't bleed into each other, and other users' content is never reachable from your chat - see Security for how we enforce that.

Models

Three AI models. One click to switch.

You can switch models from the chat settings menu. All three are cloud-hosted; no AI runs on your machine.

ModelProviderBest for
Grok (default)xAIFast chat and everyday study
GPTOpenAIHarder reasoning and structured answers
GeminiGoogleLong context and web-aware tasks

Runtime

All cloud. Nothing to install.

Paper runs in your browser. There's no desktop app, no local model, no Python environment. When you ask a question, your prompt and the retrieved passages are sent over HTTPS to Paper's servers, which call the AI provider you've selected. Your sources stay in Paper's database the whole time.

Cost

Free during beta, with a free tier after launch.

You don't bring an API key - Paper pays for every model call. Paper is free during beta, and we plan to keep a generous free tier after launch. Paid tiers may be introduced later for heavy use, very large libraries, and team workspaces.

Under the hood

A few questions we get asked a lot.

How does retrieval handle different kinds of questions?
A fact lookup, a section summary, and a compare-and-contrast question need different things from the index. Paper recognises the kind of question being asked and adjusts what context is retrieved - so a specific fact lookup doesn't get treated like a broad chapter summary.
How do you stop the AI from confidently quoting the wrong passage?
Raw similarity search is a starting point, not the answer. Paper checks retrieved passages for relevance before they reach the answering model, filtering out near-matches that are topically similar but don't actually answer the question.
What happens on a really big document?
Long documents need a different approach to chat than short ones. Paper builds a structural understanding of large sources - chapters, sections, headings, pages, and timestamps - so it can answer broad questions without getting stuck on one isolated passage, and still drop into a specific page when you need a detail.
Why citations on every claim?
An answer without a source is hard to trust and easy to fabricate. Paper grounds source-dependent claims in passages it has actually retrieved, and exposes those passages as clickable citations so you can verify the answer in one step.

Try it

Bring your own PDF.

Upload a textbook, a lecture recording, or a research paper. Free during beta, no credit card.

Get started freeRead the docs
Paper

A study workspace for students and professionals who work with large documents, lectures, and research.

Product

vs Notionvs NotebookLMRoadmapFeature requests

Resources

Help centerHow it worksSecurityFAQ

Company

AboutContact

Legal

PrivacyTerms

Made in Sydney, Australia 🇦🇺 · © 2026 Paper