Boundary criterion
Model input
Example study requires age at least 18. Synthetic subject is 17.
Apply explicitly supplied study criteria to synthetic records.
Step 01
Upload sample data, define your output schema, and provide feedback on the hardest cases.
Whether the supplied record meets every explicit study criterion.
Criteria the record explicitly fails.
Required evidence that is absent, such as documented consent.
Apply explicitly supplied study criteria to synthetic records.
Example study requires age at least 18. Synthetic subject is 17.
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 study requires age at least 18. Synthetic subject is 17."
}
result = so.run_function(
"cohort-eligibility-classification",
input_data,
)curl --fail-with-body -X POST "${SUTRO_API_URL%/}/v1/functions/cohort-eligibility-classification/run" \
-H "Authorization: Key $SUTRO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": {
"text": "Example study requires age at least 18. Synthetic subject is 17."
}
}'import sutro as so
job_id = so.batch_run_function(
name="cohort-eligibility-classification",
data="cohort_eligibility_classification.csv",
)
results = so.await_job_completion(job_id)curl --fail-with-body -X POST "${SUTRO_API_URL%/}/v1/batch-inference" \
-H "Authorization: Key $SUTRO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "cohort-eligibility-classification",
"inputs": [
{
"text": "Example study requires age at least 18. Synthetic subject is 17."
}
]
}'