Help center
Short answers to the questions teams ask first. Anything else - write to us via the contact page.
Which file types can I upload?
PDF, DOCX, TXT, and Markdown, plus scanned PDFs, TIFF files from a scanner and photos of pages (JPG, PNG, WebP, HEIC). Printed Slovak and English text in scans and photos is read with OCR, and citations from those pages are labelled; handwriting is not supported. Spreadsheets (CSV/XLSX) are on the roadmap and are rejected with a clear message rather than indexed badly.
How are citations produced?
Answers are generated only from passages retrieved from your documents; each citation maps to one of those passages with its document, page, and section. If the evidence is weak, the answer says so instead of guessing.
Is our data used to train AI models?
No. Your documents are processed to index and answer within your workspace only, and our AI subprocessor does not train on API data.
Who can see what inside a workspace?
Access follows organization membership, roles, and collection permissions, checked server-side on every operation - including before retrieval for AI answers.
What happens when we hit a plan limit?
The action that would exceed the limit is declined with a precise message naming the limit; nothing already stored is affected. Owners can upgrade or add usage packs.
Can we export or delete everything?
Yes. The owner can request a full export (a ZIP with documents and structured data) and can delete the organization, which removes documents, indexes, and conversations after a 30-day grace period.