Boundary date
Model input
Example policy: returns accepted within 30 days inclusive. Purchase was 31 days ago.
Apply operational eligibility policies, detect exceptions, and route ambiguous or inconsistent records for review.
Choose an example
Apply an explicitly provided operational eligibility policy.
Step 01
Upload sample data, define your output schema, and provide feedback on the hardest cases.
Whether all supplied operational policy conditions are satisfied.
The basis for eligibility or review.
Conditions that cannot be verified from the supplied record.
Apply an explicitly provided operational eligibility policy.
Example policy: returns accepted within 30 days inclusive. Purchase was 31 days ago.
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": "Example policy: returns accepted within 30 days inclusive. Purchase was 31 days ago."
}
result = so.run_function(
"policy-eligibility-checks",
input_data,
)curl --fail-with-body -X POST "${SUTRO_API_URL%/}/v1/functions/policy-eligibility-checks/run" \
-H "Authorization: Key $SUTRO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": {
"text": "Example policy: returns accepted within 30 days inclusive. Purchase was 31 days ago."
}
}'import sutro as so
job_id = so.batch_run_function(
name="policy-eligibility-checks",
data="policy_eligibility_checks.csv",
)
results = so.await_job_completion(job_id)curl --fail-with-body -X POST "${SUTRO_API_URL%/}/v1/batch-inference" \
-H "Authorization: Key $SUTRO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "policy-eligibility-checks",
"inputs": [
{
"text": "Example policy: returns accepted within 30 days inclusive. Purchase was 31 days ago."
}
]
}'Step 01
Upload sample data, define your output schema, and provide feedback on the hardest cases.
Whether this record needs human review.
Exceptions outside the supplied workflow tolerances.
Team that should investigate the exception.
Identify workflow exceptions that need a human review.
Purchase order total $1,000; invoice total $1,250. Example tolerance is $10.
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": "Purchase order total $1,000; invoice total $1,250. Example tolerance is $10."
}
result = so.run_function(
"exception-detection-review-routing",
input_data,
)curl --fail-with-body -X POST "${SUTRO_API_URL%/}/v1/functions/exception-detection-review-routing/run" \
-H "Authorization: Key $SUTRO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": {
"text": "Purchase order total $1,000; invoice total $1,250. Example tolerance is $10."
}
}'import sutro as so
job_id = so.batch_run_function(
name="exception-detection-review-routing",
data="exception_detection_review_routing.csv",
)
results = so.await_job_completion(job_id)curl --fail-with-body -X POST "${SUTRO_API_URL%/}/v1/batch-inference" \
-H "Authorization: Key $SUTRO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "exception-detection-review-routing",
"inputs": [
{
"text": "Purchase order total $1,000; invoice total $1,250. Example tolerance is $10."
}
]
}'