Investment document processing

Step 01

Define and Align

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

Output schema

RevenueNumber · optional: Revenue for the specifically requested reporting period.
Actual revenueNumber · optional: Reported actual revenue, separate from forecasts.
Forecast revenueNumber · optional: Forecast revenue, separate from actual results.
Organic growth percentNumber · optional: Explicit organic growth rate; not provided when only total growth is stated.
Reporting periodText · optional: The period associated with the extracted figures, such as Q3 2026.

app.sutro.sh/functions/investment-document-processing

Collecting feedback · 1/3

Extract stated investment-document facts with their qualifiers.

Example 1 of 3

Period mismatch

Model input

Document excerpt

Investment report

Synthetic report: Q3 revenue $8m; nine-month revenue $22m. Requested period: Q3.

Model output

Revenue

Actual revenue

Forecast revenue

Organic growth percent

Reporting period

Why? Optional guidance

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": "Synthetic report: Q3 revenue $8m; nine-month revenue $22m. Requested period: Q3."
}

result = so.run_function(
    "investment-document-processing",
    input_data,
)

curl --fail-with-body -X POST "${SUTRO_API_URL%/}/v1/functions/investment-document-processing/run" \
  -H "Authorization: Key $SUTRO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "input": {
    "text": "Synthetic report: Q3 revenue $8m; nine-month revenue $22m. Requested period: Q3."
  }
}'

Batch

import sutro as so

job_id = so.batch_run_function(
    name="investment-document-processing",
    data="investment_document_processing.csv",
)
results = so.await_job_completion(job_id)

curl --fail-with-body -X POST "${SUTRO_API_URL%/}/v1/batch-inference" \
  -H "Authorization: Key $SUTRO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "investment-document-processing",
  "inputs": [
    {
      "text": "Synthetic report: Q3 revenue $8m; nine-month revenue $22m. Requested period: Q3."
    }
  ]
}'