A pretrained if social security number is in a message classifier that sorts text into one of 2 categories. Use the if social security number is in a message API immediately, no training required, then adapt it to your own data when you need more.
Drop in some text and get the prediction back. No signup, no setup.
A sample of the 2 labels this pretrained classifier chooses between.
Need a label that isn't here? Clone the classifier into your Nyckel console and edit the label set to fit your data.
Once you've added this classifier to your console, you get your own copy of it behind your own endpoint. Invoke it with any HTTP client:
curl
curl -X POST "https://www.nyckel.com/v1/functions/YOUR_FUNCTION_ID/invoke" \
-H "Authorization: Bearer $NYCKEL_ACCESS_TOKEN" \
-H "Content-Type: application/json" \
-d '{"data": "The text you want to classify"}'Python
import requests
# Get an access token: https://www.nyckel.com/docs/api/overview/authentication/
token = "YOUR_ACCESS_TOKEN"
response = requests.post(
"https://www.nyckel.com/v1/functions/YOUR_FUNCTION_ID/invoke",
headers={"Authorization": "Bearer " + token},
json={"data": "The text you want to classify"},
)
print(response.json())Example response
{
"labelName": "Contains Social Security Number",
"labelId": "label_...",
"confidence": 0.92
}Trained on a Nyckel-curated dataset covering 2 if social security number is in a message categories, served on Nyckel's own infrastructure — your text snippet stays on Nyckel.
Send raw text to the invoke endpoint; the response is a label with a confidence score.
Clone it, then correct predictions and add your own samples in the console — Nyckel retrains automatically, turning this into a custom model tuned to your data.
Financial institutions can use the text classification function to monitor communications and transactions for unauthorized use of social security numbers. By identifying messages that contain these sensitive identifiers, banks can flag suspicious activities and prevent potential fraud.
Organizations can implement this function to ensure compliance with data privacy regulations, such as GDPR and HIPAA. By screening correspondence for social security numbers, companies can take proactive steps to protect customer information and avoid costly penalties.
During the application process for loans or services, businesses can utilize the identifier to check for the presence of social security numbers in submitted documents and communications. This helps to detect identity theft early and ensure that only legitimate applications are processed.
Automated customer service bots can be programmed to identify messages containing social security numbers to handle sensitive requests appropriately. This ensures that certain queries are escalated to human agents, maintaining a higher standard of privacy and security.
Companies can use this text classification to enforce internal policies related to the sharing of sensitive information. By scanning internal communication for social security numbers, organizations can educate their employees on data handling best practices and mitigate risks.
Cybersecurity teams can deploy this function as part of an incident response strategy to identify breaches involving social security numbers. Quick identification aids in rapid response efforts, helping organizations to contain data leaks and notify affected individuals.
Businesses can use the identifier to assess communications with third-party vendors that may inadvertently expose sensitive information. By monitoring these exchanges for social security numbers, companies can better manage vendor compliance and protect their data integrity.
A zero-shot classifier uses a large foundation model's general knowledge to pick between your labels — no task-specific training, so new or edited labels work immediately. A Nyckel-trained classifier has been trained on labeled examples and runs on Nyckel's own infrastructure, which typically makes it faster, cheaper per call, and more accurate on data that resembles its training set. The "Under the hood" section on this page shows which kind this classifier is, and any classifier can be adapted into a trained one by adding your own examples.
Honestly: we can't know in advance — it depends on your data stream and how closely it resembles what this classifier has seen. The reliable way to find out is to measure it on your own data: start invoking the classifier with real traffic, or upload and annotate a set of text samples in the console — make sure they look like your production data, not idealized examples. Nyckel's evaluation metrics then show you exactly how it performs on that data before you rely on it.
No classifier is perfect, so Nyckel is built around the correction loop: invokes can be captured for review, you confirm or correct predictions in the console, and corrections become training data. Over time the model adapts to your data distribution — accuracy on your traffic improves with use rather than staying fixed.
No. This if social security number is in a message classifier works out of the box — clone it into your console and you'll have your own API endpoint in under a minute. Training data only enters the picture when you want to adapt it: your corrected predictions and uploaded samples improve the model, and you can also edit the label set to match your needs.
Trying the classifier on this page is free with no signup. Cloning it requires a free account, and the free tier covers your first API calls each month — see nyckel.com/pricing for current limits and paid tiers.
Add this pretrained classifier to your Nyckel console — you'll get a live API endpoint in under a minute, and a path to a custom model when you need one.