Quoted announcement
Model input
Article investigates security failures and quotes a vendor product announcement.
Content classification
Label content by its purpose and main subject using your team’s definitions.
Choose an example
Classify documents by their substantive purpose and topic.
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
- CategoryChoose one
The document’s substantive purpose.
- security_analysis
- tutorial
- product_launch
- independent_review
- sponsored_content
- other
- Commercial intentChoose one
Whether the content primarily informs or promotes.
- editorial
- promotional
- mixed
- TopicsList of values
The substantive subjects covered in the document.
Collecting feedback · 1/3
Classify documents by their substantive purpose and topic.
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": "Article investigates security failures and quotes a vendor product announcement."
}
result = so.run_function(
"content-classification",
input_data,
)curl --fail-with-body -X POST "${SUTRO_API_URL%/}/v1/functions/content-classification/run" \
-H "Authorization: Key $SUTRO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": {
"text": "Article investigates security failures and quotes a vendor product announcement."
}
}'Batch
import sutro as so
job_id = so.batch_run_function(
name="content-classification",
data="content_classification.csv",
)
results = so.await_job_completion(job_id)curl --fail-with-body -X POST "${SUTRO_API_URL%/}/v1/batch-inference" \
-H "Authorization: Key $SUTRO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "content-classification",
"inputs": [
{
"text": "Article investigates security failures and quotes a vendor product announcement."
}
]
}'Define your own labels
Use your own classification taxonomy and accepted label values. Annotate borderline examples to teach the distinctions your team cares about, then apply the same policy to the rest of your content.