Pick the format and a seed
Choose ebook or paperback and start from a seed phrase or a recommended pick. The format changes the shelf you are comparing against.
A niche is only worth writing when buyers search for it and the shelf is thin. Demand comes from the store’s own search box; supply comes from the public pages of the books you would be up against.
Demand is free to read, but checking the shelf behind a phrase reads several public product pages. A free account keeps those lookups rate-limited and your results saved.
Choose ebook or paperback and start from a seed phrase or a recommended pick. The format changes the shelf you are comparing against.
Completion count on one side, median rank, ratings and price on the other. The score is the summary; the numbers are the argument.
A surviving phrase can prefill a new book with its title, audience and brief, so the research becomes the first page of the project.
A popular phrase with a crowded shelf is the most expensive place to publish. The tool shows both sides of the same search before you commit.
Median rank and rating counts tell you how far down a listing would sit and how much social proof the incumbent titles carry.
Everything here comes from pages any shopper can open. No scraped private data, no modelled numbers — just the shelf as it stands today.
Compare three or four phrases before writing. The one with real demand and the thinnest shelf is the one worth a month of writing.
A genre you have not published in has its own shelf conventions. Read the top titles’ rank spread before assuming your usual angle will land.
A phrase that was open last quarter may have filled up. Rerun the check before a relaunch instead of trusting a stale note.
Demand and competition are measured in the same run, against the same phrase, so the two numbers are comparable instead of stitched from different tools.
A shelf lookup is expensive. Results are stored for a month and shared with your recommended picks, so repeat research does not repeat the cost.
A surviving pick turns into a prefilled book: title, audience and brief already there, ready for the first chapter.
The store’s own autocomplete. A phrase that completes is a phrase buyers have searched often enough for the store to learn it. It is a completion signal, not a monthly volume estimate.
The public shelf behind the phrase: the books a buyer would see, with their best-seller rank, rating count and price. A thin shelf with weak ranks is room to enter; a crowded shelf of strong titles is not.
The demand half is free. Checking the shelf costs a credit per run because each check reads several public product pages, and results are cached for a month so the same lookup is not paid for twice.
Each account has a daily cap, shown in the tool. The cap moves with your plan and resets every day, so a failed experiment never locks you out of the next one.
Lower is better. A phrase whose visible books sit deep in the store is a phrase where a well-targeted listing can still be found. A shelf of top-10,000 titles with thousands of ratings is a different fight.
Yes. A shelf is a snapshot; ranks and ratings drift. Cached results carry a checked date, and a pick is re-run once the cache is older than a month.
A shared pool of phrases that already passed the demand-and-shelf check. They are starting points, not guarantees: read the evidence behind each one before you write.
No. Turning a pick into a book only prefills the title, audience and brief. The chapters are still written one at a time, against your story bible.

The interesting question is not whether the prose is pleasant. It is whether the prose obeys: a point of view, a tense, a rule, a fact, an ending.

The question is not which one writes better sentences. It is which parts of the job you are actually buying, and which parts stay with you either way.

A generator can produce a competent draft in an afternoon. It cannot produce your cases, your numbers, your taste, or the decision about what the book is willing to say.