---
sourceDocument: Australia Enable AI
sourceDocumentLink: https://servicenow-prod.fluidtopics.net/r/pt-BR/intelligent-experiences

 Release :

    - australia

ft:locale :

    - pt-BR

ft:publication_title :

    - Australia Enable AI

ft:clusterId :

    - platai

bundleId :

    - platai

workflow :

    - Platform


---

# Define the specialty

# Define the specialty of an AI agent {#ariaid-title1}

* Versão de lançamento: Australia
* 
* Atualizado 12 de mar. de 2026
* 
* ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 2 min. de leitura

In the guided setup for an AI agent, write a clear description defining your agent and its role. You can also configure supported LLMs, enable third-party access, and manage long-term memory.

## Antes de Iniciar

Role required: sn_aia.admin

## Por Que e Quando Desempenhar Esta Tarefa

The first step of the guided setup enables you to define the fundamentals of the AI agent. The description, AI agent role, and list of steps fields are used by the LLM to understand how to use the AI agent, by itself or as
part of an agentic workflow. Descriptions, AI agent roles, and list of steps should be clear and well-defined. For guidelines for writing these fields, see [Writing effectively for agentic AI](https://servicenow-prod.fluidtopics.net/nNasEloTB7j8okzURW_l3A "By following some general guidelines for creating AI agents and agentic workflows, you can create clear and effective instructions that help maximize their efficiency and effectiveness."). For an example AI agent, see [Example AI agent](https://servicenow-prod.fluidtopics.net/eVazbXHE~4_lRBAEjvwHAg "Use the example AI agent with clear name, description, AI agent role, and list of steps fields to use as a guide when creating your own AI agents.").

## Procedimento

1. Enter a name for the AI agent.
2. Craft an AI agent description.  
   The description should clarify the purpose of the AI agent, including its inputs, outputs, and context.
3. Craft the AI agent role.  
   The difference between the description and the agent role is that the agent role provides more detail about the function that the AI agent serves within a greater context. The greater context may be as part of an agentic workflow, or it could be the specific function it serves in another type of work process.


4. Craft a list of steps.  
   You can also use an old version of a list of steps. Select View versions for a full list of previous versions of the field. See [Version control](https://servicenow-prod.fluidtopics.net/uX9YniUtT4~UUtGCazrzfQ "Version control enables you to track changes made to instructions sent to the LLM for AI agents and agentic workflows.") for more information.
5. Determine unsupported model providers.  
   You may find that some models use your AI agent better than others. If you want to avoid users from having a less optimal experience with a certain model, you can mark a model as unsupported. If an administrator
   changes the instance-level settings to an unsupported model, your AI agent won't be available to users.
6. Determine if the AI agent can be accessed by third parties.  
   Make your AI agent discoverable by turning on the Allow third-party to access this AI agent toggle button that enables you to use your ServiceNow AI agent on other platforms. You can still use it on your ServiceNow instances as well.

   See [ServiceNow agents as secondary agents](https://servicenow-prod.fluidtopics.net/dsV7EgwXpVn06UPqpiaMTg "Integrate ServiceNow AI agents into other agentic AI systems, such as Google Cloud or Azure OpenAI.") for more information about configuring agents to use on other AI platforms.
7. Configure long-term memory options.  
   Long-term memory for AI agents enables agents to access data outside of the specific conversation or trigger that executes it. For example, you can select the Device and Software category to give the AI agent access to user information about the kinds of hardware devices and software that are available to the invoking user. The AI agent can remember this information in later conversations.


8. Configure AI agent learning.  
   You can enable the AI agent to learn from past interactions with the user. For example, if the user encounters a similar issue, enabling this feature could help the AI agent understand what didn't work previously, so
   it can recommend other options.  
   Nota:  
   When the agent learning capability is inactive at the AI Agent Studio level, the option to enable at the AI agent level is also inactive. To enable agent learning at the AI Agent Studio level, see [Set up long-term memory](https://servicenow-prod.fluidtopics.net/5syDjj~_ncm5iz7XIVdIjA "Make AI agents remember your preference or facts from previous interactions and use memories for more focused conversations.").

## Resultado

You have defined the basics of your AI agent.

## O que Fazer Depois

Select Save and continue to move to the next step, [Add tools and information](https://servicenow-prod.fluidtopics.net/YSxJ3JS32JPE2ffUbEqGzg "Add a tool to an AI agent to enable different functionalities and help your AI agents achieve their objectives.").