Type the question you are actually trying to answer. You get about ten papers that exist, with one sentence each on what they contribute — and the details come from the record, not from a language model.
Your question is reduced to its keywords and sent to Semantic Scholar’s Academic Graph. If that returns too little, the search falls back to OpenAlex. Both are open scholarly databases; we have no index of our own, here or in the product.
The model never supplies a title, an author, a year or a DOI. It is handed the papers the search returned, numbered, and may only pick numbers and write one sentence about each. Everything you see printed about a paper comes straight from the database record, so the tool cannot invent a reference.
The abstract, and only the abstract. Nobody has read the full text — not the model, and not us. Treat the line as a reason to open the paper, never as a summary of its findings.
The tools run on a fixed daily budget. When a day’s budget is used up they stop until it resets at midnight UTC, and the page says so instead of failing quietly.
Yes. Every paper shown comes from a Semantic Scholar or OpenAlex record, with its DOI link where the record has one, and the language model is never allowed to supply bibliographic details. If a DOI does not resolve, the record is wrong at the source — tell us and we will look.
No. There is no signup, no email and no payment. There is a small daily allowance per visitor so the tool stays available to everyone, and a fixed daily budget for the tool as a whole.
No. They are written by a language model from an abstract. Read the paper and cite the paper.
Because the search found fewer usable ones, or because papers without an abstract were dropped. A narrower question usually returns fewer and better results than a broad one.
Enter a topic. Get three to five candidate gaps, each one grounded in the abstracts of real papers and each saying which papers it rests on.
Give a topic and the position you want to argue. Get three drafts taking different angles — starting points to edit, never text to hand in.
Paste a DOI or type the details in. Reference-list entry and in-text citation, in the style you need.
Where any of these tools returns papers, they come from Semantic Scholar and OpenAlex, the same open databases the Wonders app searches. We keep no index of our own. The thesis-statement helper searches nothing at all — it has only the two lines you type.