Use case

A literature review where every claim leads back to a paper.

Keep your papers on the canvas, question them one at a time or by theme, and bring the threads together without losing where each point came from.

Try Bonscape

Why one long chat fails a literature review

All papers in one chat: A summary blurs which study said what

Papers on a canvas: Each paper is questioned in its own branch

All papers in one chat: Themes are whatever the last prompt asked for

Papers on a canvas: A theme is a branch connected to the papers it covers

All papers in one chat: Good passages sink into the scroll

Papers on a canvas: Highlights are saved to a list you can return to

From papers to an outline

  1. 01

    Add your papers

    Upload the PDFs and add links to anything you only have online.

  2. 02

    One branch per paper

    Ask for the question, method, findings and limitations of each paper separately.

  3. 03

    One branch per theme

    Connect the relevant papers and ask where they agree, disagree and leave gaps.

  4. 04

    Merge into an outline

    Draft the structure of the review, and check every claim against its source before you rely on it.

Guide

How to use AI for a literature review responsibly

AI can speed up the reading and organising parts of a literature review. It cannot be trusted to remember which paper said what unless you structure the work so that it does not have to.

The attribution problem

Put ten papers into one chat and ask for the main findings, and you will get a fluent summary. What you will not reliably get is a correct account of which study each finding came from. Claims blend, and a blended claim is worse than no claim in academic work.

One paper, one branch

The fix is structural. Add your PDFs to the canvas and give each paper its own branch, connected to that paper only. Ask the same questions of each: research question, method, sample, findings, limitations. Because the branch can see just one source, there is nothing for it to confuse.

Themes come from connections

When you are ready to compare, create a branch for a theme and connect the papers relevant to it. Ask where they agree, where they conflict and what none of them address. The set of papers behind each theme is visible on the canvas, which makes the synthesis traceable. Highlight the passages you want to keep and they are saved to a list.

For the mechanics of connecting material to chats, see context types.

What still has to be you

Check every claim you intend to cite against the paper itself. Read the papers that matter in full. Follow your institution’s rules on AI use and disclose it where required. The canvas helps you organise the reading. It does not replace it.

Bring one critical discussion to Bonscape and see how it makes every dot connect.

Try Bonscape