Skip to content
Nocta
See all work
Document AI · Workflow Automation/2026

Document Studio

SPECIMENSPECIMENSPECIMENSPECIMEN

A document studio that reads a request, drafts the reply, and signs the certificate — verbatim values where the source has them, grounded prose where it doesn't, a human in the loop before anything leaves the firm.

ClientMid-market professional services firm

Sample documents, extracted fields, drafted replies, and signed certificates shown on this page are synthetic — crafted to demonstrate the pipeline, never taken from a client's real paperwork.

0
median ingestion per document
0
accuracy vs regex baseline
0
source values pulled verbatim
0
from upload to delivered draft

Back-office work is paperwork — invoices, agreements, batch records. Document Studio reads them, pulls the fields, drafts the response, and signs the certificate. Same engine, two visual styles: verbatim where the source has the value, grounded where it doesn't.

Document Studio / interactive demo[ SYNTHETIC DATA ]
Document StudioSame engine, three modes

Triage · Draft · Certificate

Half of inbound is operational — price, stock, order status. The pipeline classifies on arrival and drafts the reply before a rep opens the email.

Inbound · classified on arrival

FromHalden Veterinary GroupEmail · 6 min ago

Could you confirm today's price for the 50mg/ml oral suspension, 100ml bottle, ex-MHRA specials catalog #CMP-0421? We have a prescription for 4 bottles this week.

IntentPrice · matches #CMP-0421

Catalog lookup

Catalog v6.2 · 412 SKUs

Reply drafted against catalog ground truth — no invented SKUs or prices.

Compliance & send

  • · Recipient class verified
  • · Jurisdiction · opt-out honored
  • · Deliverability · SPF + DKIM pass
  • · Message compliance · identity + unsubscribe present
Gates4/4 passed

Drafted reply

catalog-grounded

Verbatim pulled from the source·grounded prose around the canonical values
switch mode above

Interactive / built with synthetic data for this page

[ THE CHALLENGE ]

~3.4smedian ingestion per document

Professional-services back-office is paperwork on top of paperwork. Operators re-key the same fields out of PDFs into CRMs, draft follow-ups from the same boilerplate, hand-write certificates from the same spec, and re-key all of it into the archive — every handoff is a typo waiting to happen and a half-day waiting to be lost. The team needed every document to land already structured, with the next one already drafted, with nothing invented along the way.

How we built it

From signal to shipped.

01

Ingest any document

A hybrid parser: deterministic templates for known shapes (invoices, agreements, batch records), OCR + vision for the rest. Auto-detects file type, language, and layout.

02

Extract the canonical values

A two-layer extractor pulls canonical fields with regex/coord, then a grounded LLM pass handles the messy semi-structured bits. A confidence gate flags anything below threshold for review.

03

Two-style authoring

The drafted output puts source values in their place, no invention, then writes the prose around them — grounded on the extracted fields or the spec. Reviewers see at a glance which parts are verbatim and which were drafted.

04

Approve, sign, deliver

Drafts land in review. A qualified reviewer approves outbound, two qualified reviewers sign regulated output, then the workflow routes the draft to the right inbox and the source to the right folder. Every step auditable, end-to-end.

What shipped.

OpenRouterClaude (Anthropic)Tesseract / DocParserHandlebarsPostgreSQLDocker

Hybrid ingestion across PDF, DOCX, and image scans — median 3.4s per document.

Two-layer extraction with confidence gating; ~+34% accuracy over a regex-only baseline.

Two-style generation (verbatim vs grounded) makes every output reviewable in seconds.

One engine covers inbound triage, drafted replies, and signed certificates.

[ NEXT PROJECT ]

Sourcing Copilot