---
title: Deployment settings
description:

---

# Deployment settings

After you [create and configure a deployment](add-deploy-info), you can use the settings tabs for individual features to add or update deployment functionality: 

 Topic | Describes
-------|------------
[Set up service health monitoring](service-health-settings) | Enable [segmented analysis](deploy-segment) to assess service health, data drift, and accuracy statistics by filtering them into unique segment attributes and values. 
[Set up data drift monitoring](data-drift-settings)         | Enable [data drift monitoring](data-drift) on a deployment's Data Drift Settings tab. 
[Set up accuracy monitoring](accuracy-settings)             | Enable [accuracy monitoring](deploy-accuracy) on a deployment's Accuracy Settings tab.
[Set up fairness monitoring](fairness-settings)             | Enable [fairness monitoring](mlops-fairness) on a deployment's Fairness Settings tab. 
[Set up humility rules](humility-settings)                  | Enable [humility monitoring](humble) by creating rules which enable models to recognize, in real-time, when they make uncertain predictions or receive data they have not seen before.
[Configure retraining](retraining-settings)                 | Enable [Automated Retraining](set-up-auto-retraining) for a deployment by defining the general retraining settings and then creating retraining policies.
[Configure challengers](challengers-settings)               | Enable [challenger comparison](challengers) by configuring a deployment to store prediction request data at the row level and replay predictions on a schedule.
[Review predictions settings](predictions-settings)         | Review the Predictions Settings tab to view details about your deployment's inference data.
[Enable data export](data-export-settings)                  | Enable [data export](data-export) to compute and monitor custom business or performance metrics. 
[Set up custom metrics monitoring](custom-metrics-settings) | Enable [custom metrics](custom-metrics) monitoring by defining the "at risk" and "failing" thresholds for the custom metrics you created.
[Set prediction intervals for time series deployments](predictions-settings#set-prediction-intervals-for-time-series-deployments) | Enable [prediction intervals](ts-predictions#prediction-preview) in the prediction response for deployed time series models.