AwaitVerify routes low-confidence document extractions to a human verifier, returns a corrected typed Pydantic model, and keeps your agent pipeline running.
Drop verify_document() in next to your extraction. Humans handle the review out of band. Your agent resumes with a typed Pydantic model, no JSON parsing, no babysitting.
# your existing extraction pipeline result = your_ocr_model.extract(document) # add human verification from awaithumans import verify_document verified = await verify_document( task_description="Confirm all codes in table 3B", response_schema=Invoice, document_path="./invoice.pdf", prior_extraction=result, ) # returns a verified Pydantic model. pipeline continues. pipeline.next(verified)
Pass your document, your current extraction result, and a plain-language task description. Works with any extraction provider. Bring your own model and API key.
The document is fragmented before any reviewer sees it. The reviewer sees only what they need to verify the specific extraction in question. Screenshots disabled. Time-bound.
Once submitted, the corrected extraction comes back as a typed Pydantic model. Your pipeline resumes. The document is deleted.
Call AwaitVerify with your extracted result and get back a human-verified version, without us touching your extraction pipeline.
Pass a document and your provider's API key; we run the extraction, route to a human verifier, and return a single verified result.
A human verifies first, then an AI checks the response against your criteria and loops it back to the human with feedback if it fails.
Four teams. Four different documents that AI got confidently wrong. Four results their pipeline could not survive without.
A B2B SaaS shipped an AI document tool to enterprise customers. The product asked end-users to confirm every extracted field. Users abandoned. Renewals stalled. They called it "AI fatigue." Moving verification to AwaitVerify pulled the babysitting out of the user's hands entirely. End-users see the verified result, not a queue of "please confirm" modals.
A regional general contractor's AI cross-checked structural drawings against the bar list. OCR misread T12C3 as 712C3, the wrong rebar was ordered, six days into the pour the engineer noticed the spacing was wrong. AwaitVerify catches the misread at confidence < 0.92, before procurement ships.
A neobank in stealth needed KYC (passport, utility bill, selfie) without retaining the document set on a third-party server. The mobile SDK fragments client-side; reviewers verify fragments. The original images never touch the bank's compliance perimeter beyond their app.
A legal-tech company was extracting indemnity, termination, and payment clauses from incoming contracts. The AI was 92% right. The 8% it got wrong cost customers $40k per missed clause on average. AwaitVerify gives them a typed Clause object verified by a reviewer before it ships downstream.
We built the security model around one principle: minimize exposure at every step. Right now the only reviewers are the two founders. Every control below is in place before we expand.
Originals are split into five masked versions before any reviewer sees the document.
Documents and fragments live only in memory and are deleted the moment a reviewer submits.
All review happens on premises, on company hardware, with screenshots disabled, time-boxed tasks, ID verification, and signed NDAs.
Every task is logged (reviewer identity, timing, result) with no document content, accessible via dashboard and API.
Priced per page verified. You know how many pages you're sending. Your bill is predictable before the invoice arrives.
The verify_document() function, the self-hosted dashboard, email and Slack integrations, and the AI verification loop are all open source under MIT. You can run AwaitVerify entirely on your own infrastructure.
The hosted platform is for teams that want managed infrastructure, SLA guarantees, and the reviewer network.
view on github ↗$5 free credit. About 6 pages. No card. No sales call. Open source and free to run yourself. Hosted version for teams that want managed infrastructure and the reviewer network.