Document extraction that
actually understands.
Document extractionthat actually understands.
ProofPudding understands document structure, relationships, and context — then verifies accuracy. Built for developers who can't afford to miss what matters.ProofPudding understands document structure, relationships, and context — then
verifies accuracy. Built for developers who can’t afford to miss what matters.
$ pip install proofpudding from pudding import PuddingClient with PuddingClient(access_token="pk_your_api_key") as client: doc = client.documents.upload(file_path="report.pdf") job = client.jobs.create( document_id=doc.id, question="What were the key findings?" ) print(job.result.answer) # "The total revenues in Q4 were $12.5 million..." print(job.result.confidence) # "high"
Put it to the test
Upload any document and ask a question. Supported formats: .
Document extraction
that proves itself
Every answer traced back to the source
Any document or language
. Scans, tables, forms and 200+ pages. Japanese, Arabic, Chinese and more.
Evidence for every answer
Every value links to the exact page and source text. Verifiable by default.
Predictable costs
Pay per extraction, not per token. Budget based on task complexity.
Best-in-class accuracy
Production-ready outputs built on cross-referenced facts. No guessing, no gaps.
Minimal code, maximum data
Load, extract and use in a few lines of code
from pudding import PuddingClient client = PuddingClient(access_token="pk_your_api_key") doc = client.documents.upload(file_path="contract.pdf")
Works with your stack
Native integrations for every major agent framework
Pay per extraction
No subscriptions, no minimums
Questions
(native and scanned where applicable). More coming soon.
Our agent processes documents up to 200 pages. For longer documents, contact us.
All languages Claude supports, with particular strength in English, Japanese, Korean, Chinese, Arabic, Thai, and European languages.
We store uploaded documents (e.g., PDFs) to enable on-demand access and re-processing at your request.
LlamaParse converts documents to markdown for RAG. We extract structured data from specific queries. Parsing ≠ extraction.
Ready to extract?
$10 free credit. No card required.
$ pip install proofpudding