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

 Release :

    - zurich

ft:locale :

    - en-US

ft:publication_title :

    - Zurich Enable AI

ft:clusterId :

    - platai

bundleId :

    - platai

workflow :

    - Platform


---

# Conversational Help

# Conversational Help {#ariaid-title1}

* Release version: Zurich
* 
* Updated July 31, 2025
* 
* ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 2 minutes to read

This skill uses Generative AI application capabilities to provide answers to the questions on the ServiceNow Otto panel.
Important:  
This generative AI skill is turned on by default. The skill will be automatically available to appropriate role users for the application. For more information, see [AI agents, skills, and agentic workflows on by default](https://www.servicenow.com/docs/ptmcGIKhe~sMEt0NdnIo1g "Starting with the Zurich Patch 4 release, some AI agents, skills, and agentic workflows are turned on by default.").  
The Conversational Help skill displays as Get Help on the ServiceNow Otto panel.  
Note:  
The Get Help feature is available as a part of generative AI entitlements and no new subscription is required. The feature is enabled by default and you can turn it off in the AI Admin Hub Settings.  
You can ask your question in two ways:

* Select Get Help skill and submit a query to use the help option in the ServiceNow Otto panel.
* Submit your query directly in the ServiceNow Otto panel. It will perform discovery and find the most appropriate skill among the listed, based on the keywords you entered. This discovered skill is used to retrieve answers for your queries.  
  Note:  
  The available skills displayed in the ServiceNow Otto panel can be customized in consultation with the integration teams.
{#conversational-help-skills__ul_s2j_gd2_yfc}

## How Conversational Help works {#conversational-help-skills__section_dt1_h22_yfc}

Your query goes through the following steps to retrieve the best response.

1. AI searchThe query is sent to **central ServiceNow instance** , where **AI Search** will search the knowledge table that stores content from product doc content.

   We use Instance Data Replication (IDR) that synchronizes product documentation content from Now Support instances.  
   Note:  
   Multiple central ServiceNow instances are deployed across three regions: US East or US West, EMEA, and APJC.
2. The top matching chunks (or records) along with the user's query, are sent to the Now Assist Q\&A Genius Result configuration to generate a meaningful, contextual answer.
3. Re-rankingThe Now Assist Q\&A, an out of box (OOB) capability, re-ranks the retrieved chunks to ensure better relevance.

4. Cache lookup
   * If the user query exists in the cache, the pre-stored answer is returned.
   * If the query is not cached, the query and re-ranked chunks are sent to Now LLM to generate a meaningful answer.
   {#conversational-help-skills__ol_ml1_333_yfc}

{#conversational-help-skills__ol_dmm_d33_yfc}The Now LLM retrieves the most relevant result from <https://www.servicenow.com/docs/> portal and displays it in the same panel.  
Note:  
Effective from this release, the query will retrieve results based exclusively on the release version of the user's current instance. This enhancement is integrated into the query process to ensure the delivery of precise results that reflect the latest updates and features.

For more information, see [Fetch end points in Now Assist Conversational Help skills](https://www.servicenow.com/docs/Vy_xLLKiRe8JeJoRMbrxoA "The Now Assist Conversational Help skills architecture solves latency by fetching answers hosted at the nearest location, which is best suited to the user.").