Parse, classify, extract and instruct over documents of any length — in Indian scripts and English.
Every value cited to the exact page and region.
Four modes, each run by its own agent — use one on its own or chain them: parse a bundle, split it into documents, pull every field, then ask for whatever you need next.
DocWise builds a tree of every document, page and section you upload — so it can reason across information spread over many pages and files, the way an analyst would.
For teams whose decisions rest on documents — and who have to show their working.
Available as an API in two modes. Each value comes back with its page, bounding box and confidence — use it on its own, or as a step in a Kriyam Flow agent.
Tell us about your documents and workflow, we'll help you to find the right solution with Kriyam.
Every value, flag and verdict links back to its exact region on the page.
Kriyam Cloud, or inside your own AWS or Databricks — we’re official partners on both.
Certified information security management.
Privacy by design for India and the world.
Everything you need to know about Kriyam AI Studio. Can’t find what you’re looking for? Our team is happy to help.
Parsed text, the document type, and structured fields as JSON — every value cited to its page and region.
Yes. Send your own JSON schema with a description for each field, or let DocWise propose one.
PDF, JPG and PNG, up to 200 pages, including scans, photos, handwriting and stamps.
Yes. Documents uploaded together are indexed as one set, so answers can combine facts from different pages and files.