CurTask vs Consensus: from quick answers to a literature review you can defend

This page is for students and researchers who have used Consensus to get a feel for what the research says, and now need to turn a pile of papers into a literature review chapter. Consensus is well known as an AI search engine for scientific research that gives quick, sourced answers to research questions, including its Consensus Meter for yes-or-no questions. CurTask picks up where the searching ends: the reading, analysis and writing you do with the papers you have chosen.

At a glance

A different job: working with the papers you chose

Consensus helps you see what a body of research tends to say. A literature review asks something more: you have to read your chosen papers closely, compare them on the same points, notice where they disagree and write about it in your own voice. CurTask is built for that second stage.

Everything starts in your Global Library. You drop in PDFs, Word or OpenDocument files, including scanned papers in English or Malay, which are read on your own device. Each paper is stored once, the duplicate check stops the same paper being analysed twice, and the details are filled in from the DOI for you to edit. You can also search open research catalogues inside CurTask and add open-access PDFs in one click; a paper found without a PDF is saved and marked "No PDF", ready for the file later, and the AI analyses only papers that have their PDF.

Evidence on the page of your own copy

Consensus links its answers to the papers behind them and can show the passage a citation came from. CurTask works at the level of the passage in your own file: every AI value in the literature matrix carries a page number and a verbatim quote, and the quote is checked to exist on that page of your PDF before you see it. If no passage supports a value, the cell says "No source found" instead of offering an unsupported answer.

You add a matrix column by describing it in plain words, such as "sample size" or "main finding about teacher readiness". You see the credit estimate before anything runs, and each value stays marked Suggested until you accept, edit or restore it. That way the matrix is yours, and you can show anyone where each value came from.

Analysis you can build a chapter on

Beyond the matrix, CurTask's Analysis lens gives you qualitative coding inside the reader. Select a passage, apply a code and it appears as a coloured coding strip beside the text. Your codebook keeps colours easy to tell apart, and memos on coded passages are never sent to the AI. Coding by hand is part of every plan; on paid plans, AI codes every paper of a project at the push of a button and sorts your codes into categories and themes, each suggestion waiting for you to accept or dismiss it.

On the synthesis map you group codes into themes and mark which papers agree with, contradict or extend each other. This is where "what the research says" becomes your own argument, grounded in specific passages rather than a summary.

Writing beside your evidence

The Writing lens keeps your sources next to your draft. You write in sections you can reorder, with binder, corkboard and outline views, and cite with @ in any of eight styles, including APA, Harvard, Chicago and IEEE. The evidence line connects a citation to the exact passage in the PDF, and "Jump to the page" takes you there.

Optional marks show sentences that have no citation yet. AI text stays marked Suggested until you accept it, because the researcher is the author. When the chapter is ready, compile it to Word, PDF, Markdown or HTML.

The writing sidebar answers from your own accepted analysis instead of a general search. It reads only the matrix values, coded passages, themes and links you have accepted, shows up to three cards for the paragraph you are on (contradictions first), says where each card comes from ("From your matrix", "From your code") and shows its page and verified quote. When a claim has no accepted evidence behind it, a card says so.

Available now in the Writing lens: Check my citations asks whether each paper you cited says what your sentence says, and Claim support marks the sentences a reader would expect a source for and looks for passages that back them in your own papers; on paid plans it also suggests published studies you don't have yet. Every passage from your papers is quoted and checked on its page, and your text is never rewritten.

Costs you can see, and a library that pays you back

Every AI action in CurTask shows its cost before it runs, credits are never charged twice, and a job your balance cannot cover does not start halfway. A paper's analyses travel with it into every project it joins, so reusing them costs 0 credits. Reading, OCR, search, citations and compiling never use credits at all.

Prices are in ringgit, with a free plan, a Student plan for university students and a Researcher plan. The interface is in English and Bahasa Melayu, your work is stored in Malaysia, and it is never used to train AI.

When Consensus might suit you

If you want a fast, sourced overview of what published studies say about a question, especially a yes-or-no question, before you commit to a topic, Consensus is designed for that kind of quick exploration and does it well.

Using both

The two fit together naturally. Explore a question in Consensus, then download the PDFs of the papers you decide to read in full and drag them into CurTask. The details are filled in from each DOI. From there, your matrix, codes, themes and chapter live in one project, and every AI value points to a page in your own copy.

Try CurTask on the free plan with the papers you already have, no card needed.