Upload up to 3 sources — PDFs, Word docs, slides, spreadsheets, text files, Google Drive files, or a URL — pick the CSV Table tile, and Scholarly generates a single flat .csv with one header row and one record per row, saved to your library and ready to download. The Free plan includes one lifetime AI creation and one upload (8MB or 32 PDF pages). Premium ($30/mo or $144/yr) allows 10 AI creations per week and Laureate ($99/mo) allows 80.
Chat tools answer with a Markdown table that looks fine on screen and falls apart on import: merged headers, notes under the table, numbers formatted as text. CSV is the lowest common denominator every data tool understands, which is exactly why the CSV Table tile is strict about producing nothing but the table.
Because the generator reads your uploaded sources rather than answering from memory, the rows are your rows — the suppliers in your contract, the studies in your literature review, the SKUs in your price list. Where the document is silent, the cell is left blank so you can see the gap instead of trusting a plausible-looking filler.
The result is a real file in your Scholarly library, not text in a chat window. Download it, drop it into Sheets or a database, and keep the source file alongside it so you can always trace a value back to the page it came from.
The CSV tile is deliberately narrow. These are the boundaries to plan around.
Professionals use the CSV tile to get data out of documents that were never meant to be data: CRM lists from event PDFs, inventory records from supplier catalogues, lead lists from proposals, and compliance registers from policy binders. Name the columns once, and every document in the same family comes out in the same shape.
Teams plans add shared libraries, so a whole department can generate from the same source files and keep the resulting CSVs, spreadsheets, and SOPs in one place.