Docusplit AI is a web-based tool that splits multi-page PDFs into separate documents and names each file by its content. You pick one of two modes before uploading. In invoice mode the AI reads the invoice number, company name and date on every page. In document mode it first checks whether a page belongs to an invoice and otherwise reads the document type, the sender and the date. A continuation flag keeps multi-page documents together, for example when a page says "Page 2 of 3" or repeats the invoice number.
An invoice comes out as INV-2025-0281_Acme-Corp.pdf and a contract as Contract_Northwind-Ltd_2025-01-15.pdf, instead of scan_001.pdf. When the AI cannot read anything on a page, that page stays in the ZIP as Document_Page_7.pdf and shows up as "Not detected" in the CSV overview. Adobe Acrobat Pro splits by page count or bookmarks, and Docparser and Hazel rely on rules you set up yourself; here the split and the naming happen in the same upload, without templates.
The tool runs in the browser with nothing to install. The model reads documents regardless of language, tested on English, German, French, Spanish, Italian and Dutch; the interface and the CSV come in English and German. Files are transferred over TLS, kept only while processing and then deleted from our servers. AI analysis runs through the OpenAI API under a data processing agreement with OpenAI Ireland and Standard Contractual Clauses, is never used for training, and OpenAI retains API data for up to 30 days for abuse monitoring. See our privacy policy for details.