Current employer
Model input
Synthetic profile: Cedar 2020–2023; Birch 2023–present.
Talent profile enrichment
Turn career histories into consistent employer, skill, specialty, and seniority attributes.
Choose an example
Extract job-relevant career facts from synthetic profiles.
Step 01
Define and Align
Choose an example, review the proposed output, and annotate the fields that need to change. Your guidance defines the learned rules.
Output schema
- Current employerText · optional
Current employer, excluding roles that have ended.
- SpecialtyChoose one
Specialty supported by the documented work.
- database_operations
- data_engineering
- software_engineering
- other
- unknown
- Python yearsNumber · optional
Explicit duration of Python experience; not provided when unstated.
- Demonstrated skillsList of values
Job-related skills supported by the profile.
Collecting feedback · 1/3
Extract job-relevant career facts from synthetic profiles.
Validation accuracy
—
Example 1 of 3
3 annotations saved
Sutro can now generalize the rules based on your feedback.
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 profile: Cedar 2020–2023; Birch 2023–present."
}
result = so.run_function(
"talent-profile-enrichment",
input_data,
)curl --fail-with-body -X POST "${SUTRO_API_URL%/}/v1/functions/talent-profile-enrichment/run" \
-H "Authorization: Key $SUTRO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": {
"text": "Synthetic profile: Cedar 2020–2023; Birch 2023–present."
}
}'Batch
import sutro as so
job_id = so.batch_run_function(
name="talent-profile-enrichment",
data="talent_profile_enrichment.csv",
)
results = so.await_job_completion(job_id)curl --fail-with-body -X POST "${SUTRO_API_URL%/}/v1/batch-inference" \
-H "Authorization: Key $SUTRO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "talent-profile-enrichment",
"inputs": [
{
"text": "Synthetic profile: Cedar 2020–2023; Birch 2023–present."
}
]
}'