Auto versus property
Model input
Synthetic claim: delivery van collision damaged the van; no building damage is reported.
Route synthetic claims by their described loss and handling needs.
Step 01
Upload sample data, define your output schema, and provide feedback on the hardest cases.
The team responsible for the described loss.
The loss event explicitly described in the intake.
Details needed before routing can be completed.
Route synthetic claims by their described loss and handling needs.
Synthetic claim: delivery van collision damaged the van; no building damage is reported.
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": "Synthetic claim: delivery van collision damaged the van; no building damage is reported."
}
result = so.run_function(
"claims-intake-routing",
input_data,
)curl --fail-with-body -X POST "${SUTRO_API_URL%/}/v1/functions/claims-intake-routing/run" \
-H "Authorization: Key $SUTRO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": {
"text": "Synthetic claim: delivery van collision damaged the van; no building damage is reported."
}
}'import sutro as so
job_id = so.batch_run_function(
name="claims-intake-routing",
data="claims_intake_routing.csv",
)
results = so.await_job_completion(job_id)curl --fail-with-body -X POST "${SUTRO_API_URL%/}/v1/batch-inference" \
-H "Authorization: Key $SUTRO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "claims-intake-routing",
"inputs": [
{
"text": "Synthetic claim: delivery van collision damaged the van; no building damage is reported."
}
]
}'