Document intake & extraction

Identify incoming document types, flag incomplete submissions, and extract invoice and purchase-order fields.

Choose an example

Identify incoming document types and route incomplete submissions for review.

Step 01

Define and Align

Upload sample data, define your output schema, and provide feedback on the hardest cases.

Output schema
TypeChoose one

Document type supported by its contents.

  • invoice
  • quote
  • credit_note
  • purchase_order
  • needs_review
ReadabilityChoose one

Whether the source is legible enough to classify.

  • readable
  • partially_readable
  • unreadable
Review requiredYes / No

Whether missing or unreadable information prevents reliable intake.

  • true
  • false
app.sutro.sh/functions/document-classification-intake
Collecting feedback · 1/3
Identify incoming document types and route incomplete submissions for review.
Example 1 of 3

Quote versus invoice

Model input
Document excerpt
Incoming document

Document says QUOTATION, valid for 30 days, and contains estimated prices; no payment due.

Model output
Type
Readability
Review required

Step 02

Model Sweep

Compare quality and cost on your examples, then choose a model or use Sutro’s default.

Compare models on expert agreement and cost. The interactive chart uses illustrative measurements.

Illustrative sweep · select Value or Best to use that model in your function.

Step 03

Deployment

Call Sutro Functions like any other software. Swap the model as soon as something more performant is released.

Selected modelWaiting for sweep results.

Real-time

import sutro as so

input_data = {
    "text": "Document says QUOTATION, valid for 30 days, and contains estimated prices; no payment due."
}

result = so.run_function(
    "document-classification-intake",
    input_data,
)

Batch

import sutro as so

job_id = so.batch_run_function(
    name="document-classification-intake",
    data="document_classification_intake.csv",
)
results = so.await_job_completion(job_id)

Ready to get started?

Book time with the team

Join the self-serve waitlist

What are your bottlenecks? (Select any that apply)