---
sourceDocument: Brazil Conversational Interfaces
sourceDocumentLink: https://www.servicenow.com/docs/r/conversational-interfaces
Release :
- brazil
ft:locale :
- en-US
ft:publication_title :
- Brazil Conversational Interfaces
ft:clusterId :
- convint
bundleId :
- convint
workflow :
- Platform
---
# Migrating NLU topics to LLM
# Migrating NLU/keyword Virtual Agent topics to LLM topics {#ariaid-title1}
Release version: Brazil
Updated September 10, 2026
 5 minutes to read
Summarize
 Summarized using AI
This content was generated using new OpenAI-powered functionality. Results are provided on an as is basis and are not guaranteed to be accurate or complete.
## Summary of Migrating NLU/keyword Virtual Agent topics to LLM topics
Starting with the Brazil release, ServiceNow is transitioning Virtual Agent topics from Natural Language Understanding (NLU) and keyword models to Large Language Model (LLM) topics.
This migration supports the upcoming deprecation of Virtual Agent for NLU and Virtual Agent Lite on new instances.
The migration workflow allows you to convert your existing NLU/keyword topics into LLM topics without manually recreating them, preserving the original topics intact and creating new LLM-compatible copies.
Show full answer Show less
## Key Features
* **Supported Asset Types:** Topics, topic blocks, setup topics, small talk, custom input controls, and custom response controls can be migrated. Topic blocks are automatically published after migration; other asset types can be optionally published.
* **Roles and Access:** Migration functions are accessible to users with `virtualagentadmin` or `snvadgenai.topicmigrationadmin` roles, through the Virtual Agent Assistant Designer interface.
* **Topic Descriptions:** During migration, generative AI can create enhanced LLM topic descriptions by pulling utterances or keywords, or you can retain existing descriptions. The Detail description field is mandatory for LLM topics and can be edited during migration review. It is recommended to avoid using raw NLU utterances as LLM descriptions since LLM descriptions require more detailed context.
* **Node Descriptions:** NLU input node prompt values migrate into LLM Detail description fields. Text-only prompts transfer as-is, while prompts containing scripts or data pills are replaced with a generic template ("Collect + Node name") that should be updated post-migration for better clarity and user experience.
* **Entity and Vocabulary Migration:** Entities mapped in NLU nodes migrate into LLM nodes with additional instructions to aid data extraction. Vocabulary sources from NLU text nodes migrate into static or dynamic choice nodes in LLM topics, preserving selections and tables appropriately.
* **System Properties:** The property `snvadgenai.utterances.count.for.topic.description` controls how many NLU utterances are used to generate LLM topic descriptions during migration.
* **Migration Logs and Issue Tracking:** Migration status and issues are tracked in the `topicmigrationexecutionitem` table, accessible via the navigation pane or downloadable as a CSV file for review and troubleshooting.
## Practical Outcomes for ServiceNow Customers
* You can efficiently upgrade your Virtual Agent topics to leverage generative AI capabilities without losing existing configurations or content.
* The migration process is designed to minimize manual effort by automating the creation of LLM-compatible topics and preserving key metadata and entities.
* Post-migration, you have full control to review and enhance topic and node descriptions, improving Virtual Agent interaction quality.
* Maintaining both original NLU/keyword and new LLM topics during transition ensures continuity and fallback options.
* Clear role-based access and system properties allow administrators to tailor migration behavior and monitor migration health effectively.
The topic migration workflow enables you to migrate your existing Natural Language Understanding (NLU)/keyword topics into new large language model (LLM) topics.
Starting with the Brazil release, Virtual Agent for NLU and Virtual Agent Lite are being prepared for future deprecation. It will eventually be hidden and no longer activated on new instances but will continue to be supported. For details, see the [Deprecation Process \[KB0867184\]](https://support.servicenow.com/kb_view.do?sysparm_article=KB0867184) article in the Now Support Knowledge Base.
ServiceNow Otto capabilities bring generative AI to Virtual Agent using LLM topics. With topic migration, there's no need to manually recreate all your NLU and keyword topics to be LLM topics. You can select the topics that you want to migrate into LLM topics from your existing NLU and keyword topics. Migrating NLU and keyword topics doesn't change the original NLU or keyword topics. A copy of the existing topic is created during topic migration, but the new topic's Model Type field is set to LLM and includes LLM-compatible nodes and
descriptions.
All types of topics can be migrated from the NLU/Keyword model type to the LLM model type during topic migration, including the following asset types:
* Topic
* Topic block
* Setup topic
* Small talk
* Custom input control
* Custom response control
{#llm-topic-migration__ul_xmk_vgt_w1c}
If no migration issues occur, the preceding asset types can all optionally be published except the topic block. Although dynamic topic blocks can be optionally published, the topic block type is automatically published after it's
been migrated.
## Roles and accessibility {#llm-topic-migration__section_tjw_csf_bbc}
Users with the virtual_agent_admin role or sn_vad_genai.topic_migration_admin role can work with topic migration. Topic migration is accessible through Virtual Agent Assistant Designer in the Migrate Topics to LLM option.
Figure 1. Migrate Topics to LLM option in Virtual Agent Assistant Designer
## System properties {#llm-topic-migration__section_c1d_y3d_3fc}
Use the system property sn_vad_genai.utterances.count.for.topic.description to set the maximum number of NLU utterances that can be given to the LLM to generate the topic description for an NLU topic migrated
to an LLM topic.
## Topic descriptions {#llm-topic-migration__section_sbk_qcc_y1c}
When migrating NLU topics to LLM topics, you can choose whether you want to have generative AI create your LLM topic descriptions. When on the Settings step of the topic migration workflow, you can choose to
Keep current topic descriptions?. The Keep current topic descriptions? option is off by default. When this setting is off, generative AI pulls either NLU intent utterances or keywords from topics to create LLM topic descriptions during the migration process. If the topic is associated with an intent, a maximum of 10 utterances are pulled into the LLM
topic's Detail description field under an Additional instructions value. When this setting is on, generative AI doesn't create LLM topic descriptions and your existing NLU and keyword topic descriptions migrate into your new LLM topics. Migrating existing topic descriptions can result in issues if the existing topic doesn't have a description.
The Detail description field is required for LLM topics but not for NLU/keyword topics. If a new LLM topic is migrated over with an empty description, you must add a description prior to that topic being published. Regardless of how topic descriptions migrate, you can edit topic descriptions during the Review descriptions step of the topic migration workflow. You can also test your topic descriptions against the original NLU topic's utterances, if applicable, to improve relevance and topic description strength.
Note:
NLU utterances themselves are not effective if you use them as topic descriptions for LLM topics. Avoid using NLU utterances for LLM topic descriptions. LLM topic descriptions require more specific detailed information.
For more information on editing topic descriptions, see [Migrate NLU topics to LLM topics](https://www.servicenow.com/docs/t6TYnmw8EkDFGN37aPTfjA "Migrate one or more of your existing Natural Language Understanding (NLU) or keyword topics into new large language model (LLM) topics while maintaining your original NLU/keyword topics. After migration is complete, choose whether to publish your new LLM topics."). For examples of strong topic descriptions, see [LLM description and instruction guidelines for Virtual Agent topics](https://www.servicenow.com/docs/s0NHFogRF~5wBCsJNrbI1g "When you create large language model (LLM) topics, you provide instructions that determine the behavior of the LLM and a description that determines how the topic is discovered by the LLM.").
## Node descriptions {#llm-topic-migration__section_r1d_scc_y1c}
Although NLU topics' node names migrate exactly as-is during migration, the node descriptions can vary. NLU input nodes use the Prompt field. LLM input nodes use the Detail description field. During topic migration, the value in the
Prompt field migrates into the Detail description field's value. How the value migrates can vary depending on if that value included text-only, scripts, or data pills. Refer to the
following table to view how the values migrate differently and compare examples.
{#llm-topic-migration__table_d4r_lhr_y1c__entry__2}
| NLU Prompt field value | LLM Detail description field value |
|-|-|
| Contains text | Migrates text as-is. For example, if the NLU Prompt field's value is Enter the incident number, then the LLM Detail description field's value is also Enter the incident number. |
| Contains script or data pill | Migrates using the following template: Collect + Node name. For example, if you have an NLU node named Get incident number and the Prompt field's value contains a script or data pill, then the migrated LLM node's Detail description field's value is Collect Get incident number. |
[Table 1. How the Prompt field's value migrates to the Detail description field's value]
{#llm-topic-migration__table_d4r_lhr_y1c}
If the topics that you plan to migrate include scripts or data pills in their existing Prompt field, review and update the LLM Detail description field after migration for each affected
topic. A warning message of Add relevant detail description appears for LLM topics on the Virtual Agent Designer canvas for each node that migrated with the template of Collect + Node name. Updating the description to something more accurate and descriptive improves your users'
experience of interacting with the Virtual Agent. For an example of a strong node description, see [LLM description and instruction guidelines for Virtual Agent topics](https://www.servicenow.com/docs/s0NHFogRF~5wBCsJNrbI1g "When you create large language model (LLM) topics, you provide instructions that determine the behavior of the LLM and a description that determines how the topic is discovered by the LLM.").
The following entities can be migrated from NLU nodes to LLM nodes:
* simple
* mapped
* pattern
* system-derived
{#llm-topic-migration__ul_bt5_ttf_bbc}
If an NLU node is mapped to an entity, those utterances' entities are added to the LLM node's Detail description field under an Additional instructions:
make-shift header value. The Additional instructions: content differs slightly depending on the type of entity that is migrated. The layout of the Detail description field value
resembles something like the following:
* \[Prior NLU Prompt field value\] if the value was text-only and not a script or data pill.
* \[Additional instructions: For this input, the data should be extracted from the user input if it has a value from this list of words: \[simple entity word list\].
{#llm-topic-migration__ul_b1c_h5f_bbc} Figure 2. Example of an NLU node with associated entities migrating to an LLM node
If you had vocabulary sources established in your NLU topic's text nodes, the list and table vocabulary sources migrate into LLM nodes. Text nodes with list vocabulary sources are migrated into static choice nodes. The vocab source selections appear in
the LLM static choice node's Detail description field under an Additional instructions: make-shift header value. Text nodes with table vocabulary sources are migrated into dynamic
choice nodes. The vocabulary source's table is migrated into the LLM dynamic choice node's Table field. The vocabulary source selections are migrated into a script and appear in the LLM dynamic choice node's
Detail description field under an Additional instructions: make-shift header value.
## Migration issues {#llm-topic-migration__section_npt_vtc_y1c}
You can access migration issue data either by searching for topic_migration_execution_item.list in the Navigation pane or downloading the .CSV file version of the table. After you've migrated topics, the
downloadable .CSV file is accessible through the Review migration log option in the topic migration's Migrate topics step. For more information about migration issues, see [NLU to LLM migration log](https://www.servicenow.com/docs/CXdk~rbiAmK7vCD9YzO6Sw "The Topic Migration Execution Items [topic_migration_execution_item.list] table includes data when migrating Natural Language Understanding (NLU) topics to large language model (LLM) topics such as the migration status, migration issues, and migrated or published topic information.").
* **[Migrate NLU topics to LLM topics](https://www.servicenow.com/docs/t6TYnmw8EkDFGN37aPTfjA)**
Migrate one or more of your existing Natural Language Understanding (NLU) or keyword topics into new large language model (LLM) topics while maintaining your original NLU/keyword topics. After migration is complete, choose whether to publish your new LLM topics.
* **[NLU to LLM migration log](https://www.servicenow.com/docs/CXdk~rbiAmK7vCD9YzO6Sw)**
The Topic Migration Execution Items \[topic_migration_execution_item.list\] table includes data when migrating Natural Language Understanding (NLU) topics to large language model (LLM) topics such as the migration status, migration issues, and migrated or published topic information.