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

 Release :

    - xanadu

ft:locale :

    - en-US

ft:publication_title :

    - Xanadu Enable AI

ft:clusterId :

    - platai

bundleId :

    - platai

workflow :

    - Platform


---

# Issue Auto Resolution Tuning in NLU

# Issue Auto Resolution Tuning in NLU {#ariaid-title1}

* Release version: Xanadu
* 
* Updated April 17, 2026
* 
* ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 1 minute to read

Use the NLU Workbench homepage to support Issue Auto Resolution (IAR) tuning in NLU.

## Summary usage and roles {#issue-auto-resolution-tuning-nlu__section_up3_2tj_fyb}

Use the nlu_admin or admin role to access IAR Tuning in the NLU Workbench. Accessing IAR Tuning in the NLU Workbench requires at least the nlu_feedback_admin role (the nlu_admin role contains the nlu_feedback_admin role). Also, the virtual_agent_admin role contains the
nlu_admin role.

Selecting a IAR model name in the list takes you to tuning. For Issue Auto Resolution, you are not taken to a model overview page, so this behavior differs from Virtual Agent or AI Search models in the NLU Workbench.

## The IAR Tuning workflow {#issue-auto-resolution-tuning-nlu__section_qjf_hsj_fyb}

IAR admins begin their model tuning journey in the IAR Admin Console, and then land in the NLU Workbench to tune their ITSM model. If they haven't trained the ITSM model in the console yet, the workflow sends them to the Expert Feedback Loop documentation under the Boost your model performance section of the NLU Workbench.

## How IAR models differ from NLU models {#issue-auto-resolution-tuning-nlu__section_fvz_nvr_fyb}

Unlike the Virtual Agent and AI Search tabs, the IAR tab doesn't use a Create new model button. The IAR-ITSM model that IAR admins use is a prebuilt model. IAR models can't be moved using update sets.

## Exploring the NLU Workbench {#issue-auto-resolution-tuning-nlu__section_oh4_gv5_gyb}

At the top of the NLU Workbench page are three tabs that group Virtual Agent, Issue Auto Resolution, and AI Search models separately. Below those tabs are a list of models colored gray. In the Model column of the list, when you select the caret to the left of the model name, the model changes
color from gray to white and opens to show the model's languages; status; usage; model type; number of enabled intents and mapped intents and the date when the model was last modified or last published.
* **[Issue Auto Resolution tuning options](https://servicenow-prod.fluidtopics.net/uflOhkWnk4NgGYD0bmtAHw)**   
  When you are tuning your Issue Auto Resolution model in NLU Workbench, you can adjust the output for several goals: precision, automation, or a balance of the two. Compare how your choice of tuning options affect match rate and coverage, before committing.