---
sourceDocument: Yokohama Enable AI
sourceDocumentLink: https://servicenow-prod.fluidtopics.net/r/yokohama/intelligent-experiences

 Release :

    - yokohama

ft:locale :

    - en-US

ft:publication_title :

    - Yokohama Enable AI

ft:clusterId :

    - platai

bundleId :

    - platai

workflow :

    - Platform


---

# Configuring evaluations

# Configuring evaluations {#ariaid-title1}

Release version: Yokohama  
Updated September 2, 2025  
![](https://www.servicenow.com/docs/portal-asset/ico-clock) 1 minute to read  
Configure conversation evaluations by disabling evaluations, adjusting execution logic and thresholds, and tuning scoring weights.

## Disable evaluations {#ai-eval-config__section_k21_pxf_ngc}

Prerequisites

Update must be created.  
Disable evaluations:

1. Navigate to Process AutomationFlow Designer and select Flows.
2. Select the Execute Evaluation flow.
3. Select Deactivate.
{#ai-eval-config__ol_i5p_sby_hgc}

## Change the evaluation execution conditions {#ai-eval-config__id_odb_dqg_ngc}

Change the evaluation execution conditions:

1. Navigate to System DefinitionScript Includes.
2. Search for and select the script Include evalExecuteCondition.
3. In the Script field, modify the executeEvaluation method.
   * Input: The method receives the conversation reference record as a parameter.
   * To restrict by user profile, use the initiatedUser variable (contains the user's sys_id).
   {#ai-eval-config__ul_pm1_gqg_ngc}
4. Use GlideRecord queries or other logic as needed to implement custom execution conditions.
5. Save and test in a non-production environment before promoting.
{#ai-eval-config__ol_vj4_hqg_ngc}

## Set the daily limit on evaluations {#ai-eval-config__id_obp_xsg_ngc}

Set a maximum daily limit on evaluations:

1. Navigate to AllSystem PropertiesAll Properties (sys_properties.list).
2. Search for and select the property sn_na_conv_eval.maxEvaluateCount.
3. Set the Value field to the desired integer value to limit the maximum number of evaluations created per day.
{#ai-eval-config__ol_fhp_btg_ngc}

## Configure the minimum records for error bands {#ai-eval-config__id_xj3_3tg_ngc}

Set the minimum number of records required to calculate the error band for upper and lower deviation:

1. Navigate to AllSystem PropertiesAll Properties (sys_properties.list).
2. Search for and select the property sn_na_conv_eval.errorBandMinRecords.
3. Set the Value field to the desired integer value to define the minimum number of records required before upper and lower error bands are calculated.
{#ai-eval-config__ol_xzl_jtg_ngc}

## Adjust skill weights for the composite score {#ai-eval-config__section_v5h_ptg_ngc}

Set the weights for each evaluation metric for chat evaluation, which are used to compute total and composite scores on evaluation records:

1. Navigate to AllSystem PropertiesAll Properties (sys_properties.list).
2. Search for and select the property sn_na_conv_eval.evalWeights.
3. Update only the value components for each skill.The composite score is calculated as Sum(Skill Score × Skill Weight) / Sum(Skill Weights).

{#ai-eval-config__ol_a1x_qtg_ngc}

*[\>]: and then