Former role
Model input
Profile: Maya was VP Sales at Cedar until 2023. She is now COO at Birch.
Extract company and role attributes from collected source text.
Step 01
Upload sample data, define your output schema, and provide feedback on the hardest cases.
The person’s current company, excluding past employers.
The person’s current role or title.
The company’s stated commercial model.
Employee count only when stated; not provided otherwise.
Extract company and role attributes from collected source text.
Profile: Maya was VP Sales at Cedar until 2023. She is now COO at Birch.
Sutro can now generalize the rules based on your feedback.
Step 02
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
Call Sutro Functions like any other software. Swap the model as soon as something more performant is released.
import sutro as so
input_data = {
"text": "Profile: Maya was VP Sales at Cedar until 2023. She is now COO at Birch."
}
result = so.run_function(
"company-people-enrichment",
input_data,
)curl --fail-with-body -X POST "${SUTRO_API_URL%/}/v1/functions/company-people-enrichment/run" \
-H "Authorization: Key $SUTRO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": {
"text": "Profile: Maya was VP Sales at Cedar until 2023. She is now COO at Birch."
}
}'import sutro as so
job_id = so.batch_run_function(
name="company-people-enrichment",
data="company_people_enrichment.csv",
)
results = so.await_job_completion(job_id)curl --fail-with-body -X POST "${SUTRO_API_URL%/}/v1/batch-inference" \
-H "Authorization: Key $SUTRO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "company-people-enrichment",
"inputs": [
{
"text": "Profile: Maya was VP Sales at Cedar until 2023. She is now COO at Birch."
}
]
}'