---
sourceDocument: Brazil Enable AI
sourceDocumentLink: https://www.servicenow.com/docs/r/intelligent-experiences

 Release :

    - brazil

ft:locale :

    - en-US

ft:publication_title :

    - Brazil Enable AI

ft:clusterId :

    - platai

bundleId :

    - platai

workflow :

    - Platform


---

# Managing evaluation cost

# Managing evaluation cost {#ariaid-title1}

Release version: Brazil  
Updated September 15, 2026  
![](https://www.servicenow.com/docs/portal-asset/ico-clock) 1 minute to read  
Reduce the assists that evaluation consumes by adjusting what you evaluate, how often you evaluate it, and which AI systems you evaluate.

Evaluating both ServiceNow and external AI systems consumes assists. Three settings determine how many assists your evaluations consume.

* Consider which metrics require evaluation. Each metric increases the visibility you gain into a session but also increases assist usage to evaluate it. Evaluate only the metrics that give you the insight you need.
* Adjust the sample rate as needed. A higher sample rate evaluates more executions and gives you more confidence in your scores but also increases assist usage. Set the lowest rate that produces enough evaluated sessions to trust the score. ServiceNow AI systems use a single sample rate for all metrics. External AI systems have a sample rate per metric, so you can keep higher rates for the metrics that matter most and sample the rest.
* Evaluate AI systems that require oversight. Evaluation runs for every AI system that has it turned on, so turn it off for the systems that you don't need to monitor, such as test or retired systems.
{#mon-ai-managing-evaluation-cost__ul_eval_cost_levers}
**Related tasks**   

* [Enable evaluation for an AI system](https://www.servicenow.com/docs/COZGOuCx0eYsJ7iVVIx71A "Start generating quality and safety scores for one or more AI systems by enabling evaluation from the inventory.")
* [Disable evaluation for an AI system](https://www.servicenow.com/docs/O55eKvay9b7Cm8AhGLYotw "Stop generating evaluation scores for one or more AI systems by disabling evaluation from the inventory, while preserving all historical score data.")
* [Configure global metrics for ServiceNow AI systems](https://www.servicenow.com/docs/WgaSnUdZR03vHs~XLYsE6w "Choose which metrics to evaluate for ServiceNow AI systems and optionally adjust the shared sample rate.")
* [Configure global metrics for external AI systems](https://www.servicenow.com/docs/Zhc3vrepL~hf2vxFH4asmg "Choose which metrics evaluate all your external AI systems by default, exclude an individual system from a specific metric, and adjust how often each metric runs.")
* [Configure asset-specific metrics for ServiceNow AI systems](https://www.servicenow.com/docs/rNvIuEVY6SnP2vgFgDhFVg "Add or remove metrics for one or more ServiceNow AI systems, without changing your organization's global metric configuration.")
* [Configure asset-specific metrics for external AI systems](https://www.servicenow.com/docs/~twQJY2QMaem3I79dc0DWw "Add or remove metrics for one or more external AI systems without changing the global metric configuration, and adjust metric sample rates.")
* [Configure metrics evaluated for an AI system](https://www.servicenow.com/docs/PYQcHeLFPCx~8irCYZQS4A "Add or remove metrics for a specific AI system to tailor evaluation coverage without changing your organization's global metric configuration.")