Review and Improve Predictions

A Nyckel prediction endpoint gets more accurate as you provide feedback. Every correction you make becomes a training example that improves the model.

Every correction flows back through the same Input → Prediction → Review → Improved-endpoint cycle described in The feedback loop. This page focuses on the human side of that cycle: where to do the reviewing, and how to spend that review time well.

Reviewing predictions in the console

1. Open your function in the Nyckel console.
2. Go to the Invoke or Samples tab to see recent predictions.
3. For any prediction, click to correct the label if it was wrong.
4. Nyckel retrains automatically after you save corrections.

Reviewing predictions via the API

When your application sends a prediction to users, capture the outcome. If a user corrects or confirms a prediction, submit that feedback as an annotation:

POST https://www.nyckel.com/v1/functions/{functionId}/samples/{sampleId}/annotation
Authorization: Bearer {your_access_token}
Content-Type: application/json

{
  "labelName": "Billing"
}

This tells Nyckel the correct answer for that input.

Using confidence scores to prioritize review

Not all predictions need review. Focus your effort where the model is least certain.

• High confidence (above ~0.90): Usually correct. Spot-check occasionally.
• Medium confidence (0.60–0.90): Worth reviewing when possible.
• Low confidence (below ~0.60): Review these first — corrections here improve the model the most.

See Confidence scores and thresholds for a detailed discussion.