CurTask vs SciSpace: one project for your library, analysis and thesis chapter

This page is for students and researchers who use, or are considering, SciSpace and want to know how CurTask compares for a thesis or journal literature review. SciSpace is well known as a broad AI research assistant: it searches the literature, lets you chat with PDFs, extracts details across papers into tables and offers writing and citation tools. CurTask focuses on one connected workflow, from your own papers to a finished chapter, with every AI value tied to a page you can check.

At a glance

One project, three lenses

SciSpace offers many tools side by side. CurTask is organised around the project, the way a thesis chapter or review article actually takes shape. Each project has three lenses over the same papers: Library to collect and read, Analysis to extract, code and synthesise, and Writing to draft and cite. What you learn in one lens is there in the next, so a coded passage can become a theme, and a theme can go into your draft with its passages attached.

Your papers live once in a Global Library, and each project draws its set from it. You drop in PDFs, Word or OpenDocument files; the duplicate check means the same paper is never stored or analysed twice, and the details are filled in from the DOI. Scanned pages are read in English and Malay on your own device, which helps with older local journals and theses. A paper you only have the details of is saved and marked "No PDF"; the AI analyses only papers with their PDF, and you can add the file later.

Evidence checked on the page of your own copy

SciSpace gives citation-backed answers, and its chat citations take you to the page an answer came from, which is useful when exploring. CurTask adds a check in your own files: 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 it is shown. If nothing in the paper supports a value, the cell says "No source found" rather than filling the gap.

Every AI value is marked Suggested until you accept it, edit it or restore it. That keeps a clear line between what the AI proposed and what you, the researcher, decided, which matters when a supervisor or examiner asks where a figure came from.

Qualitative analysis built in

CurTask treats a literature review as qualitative work, not only extraction. In the reader you select a passage, apply a code, and a coloured coding strip appears beside the text. The codebook keeps colours easy to tell apart, memos on coded passages are never sent to the AI, and codes from your other projects are offered when they fit. 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.

The synthesis map turns codes into an argument. On a board or a mind map you group codes into themes and mark which papers agree with, contradict or extend each other, then send a theme to Writing with its passages.

Writing that stays connected to the source

In the Writing lens you draft in sections you can reorder, with binder, corkboard and outline views. Cite with @ in any of eight styles, including APA, MLA, Chicago, Harvard and IEEE, and the bibliography is rebuilt whenever you change style. The evidence line links each citation back to its passage in the PDF, and the Evidence panel shows the linked passage for every citation in the paragraph you are on.

Optional marks show sentences that have no citation yet, and AI text stays Suggested until you accept it. Compile to Word, PDF, Markdown or HTML when you are ready.

The writing sidebar builds on your own accepted analysis. 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), labels each card with where it comes from ("From your matrix", "From your theme"), and shows its page and verified quote. If nothing you have accepted relates to the paragraph, no AI runs and nothing is charged.

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.

Predictable costs and a library that grows in value

Every AI action in CurTask shows its cost before it runs. Credits are reserved when a job starts and never charged twice, and a job your balance cannot cover does not start. 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.

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

When SciSpace might suit you

If you want a wide toolbox in one place, such as quick literature searches, chatting with individual PDFs in many languages, paraphrasing and formatting for journal templates, SciSpace covers a broad range of tasks and may suit you well.

Using both

You can explore topics and individual papers in SciSpace, then bring the PDFs you want to analyse in depth into CurTask by dragging the files in. Details are filled in from each DOI. From then on, your matrix, coding, themes and chapter sit in one project, with each AI value traced to a page in your own copy.

Start on CurTask's free plan with a handful of your own papers, no card needed.