Importing, parsing, tagging documents
Writing, formatting, citing, editing
Exporting, compression, secure sharing
CITE is built to ingest the files investigators and analysts already use: PDFs (including scans), Office documents, images, spreadsheets, and many other common formats (more than 100 types). Imported supporting documents receive identifiers for citation. Scanned PDFs and images can be OCR’d so text becomes searchable. Non-PDF sources can be embedded as attachments in the project/export so they travel with the report.
OCR turns scanned pages and images into searchable text inside CITE’s document tools so you can find passages without retyping. OCR is a document-processing feature (local to your install’s processing path); it is separate from optional generative AI. You choose when OCR runs (for example on import or when generating a linked PDF). Use it when sources are image-based; born-digital PDFs often need little or no OCR.
Yes. Supporting documents can be organized and inspected in the project so investigators can find and cite the right exhibit quickly. Use consistent naming, folders/templates, and citation styles your team agrees on. Global search across the project helps locate text once OCR or born-digital text is available. For team handoffs, standardize templates and citation formatting so the next reader knows how the file is structured.