---
sourceDocument: Australia Build or modify applications
sourceDocumentLink: https://www.servicenow.com/docs/r/application-development

 Release :

    - australia

ft:locale :

    - en-US

ft:publication_title :

    - Australia Build or modify applications

ft:clusterId :

    - cadev

bundleId :

    - cadev

workflow :

    - Development, Data, and Analytics


---

# AI capabilities

# AI capabilities for enhancing custom applications {#ariaid-title1}

* Release version: Australia
* 
* Updated July 24, 2026
* 
* ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 4 minutes to read

Summarize  
![AI sparkle icon](https://servicenow.com/docs/portal-asset/ai-sparkle-icon) 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 AI capabilities for enhancing custom applications

ServiceNow Otto for App Engine offers a range of AI capabilities designed to enhance custom applications by integrating generative AI features.
These capabilities include Skills, AI agents, and Agentic workflows, each providing different levels of customization and functionality to automate and improve business processes within your custom applications.
Show full answer Show less  

## Skills

Skills are generative AI capabilities on the ServiceNow AI Platform that perform specific tasks like generating summaries. Key components of a skill include:

* **Input:** Data analyzed, typically records in tables.
* **Prompt:** Instructions for the large language model (LLM) defining the task and output style.
* **Output:** Generated response, which can be plain text, structured data, or formatted content.
* **Activation Methods:** Ways to access skills, such as conversationally in the Otto panel, UI actions, or Virtual Agent interactions.

Skills can be platform preconfigured (Platform generative AI skills) or custom-built using AI Skill Kit. Platform skills address common use cases but require significant reconfiguration for custom apps, while custom skills are designed specifically for your custom applications during creation.

Starting with version 28.2.4, a custom app record summarization skill template is available to generate AI summaries of records within custom tables and apps.

## AI Agents

AI agents are generative AI capabilities equipped with LLM instructions and tools to perform defined roles and tasks. Components include:

* **AI Agent Role:** Defines capabilities and responsibilities.
* **List of Steps:** Instructions guiding the agent's actions.
* **Tools:** Additional resources like skills and data sources.
* **Trigger and Availability:** How the agent is activated and where it is available (Otto panel or Virtual Agent).

AI agents can be preconfigured platform agents or custom agents created via AI Agent Studio. Custom agents are designed to integrate smoothly with your custom applications.

## Agentic Workflows

Agentic workflows orchestrate one or more AI agents with a set of LLM instructions to achieve specific business objectives, such as task classification or email processing. They include:

* **AI Agent Orchestrator:** Coordinates work flow between AI agents.
* **AI Agent Communicator:** Facilitates communication among agents and orchestrator.

Similar to AI agents, agentic workflows can be platform preconfigured or custom-built for your applications, with custom workflows providing more straightforward integration during development.

## Practical Considerations for ServiceNow Customers

* Choosing between platform and custom AI capabilities depends on your use case and the ease of integration within your custom apps.
* Platform capabilities offer ready-made solutions but often require substantial duplication and reconfiguration for custom app use.
* Custom skills, AI agents, and agentic workflows can be designed specifically for your application needs, enabling smoother integration and tailored functionality.
* Activation methods and governance, such as data steward approvals, ensure compliance and controlled deployment of AI capabilities.

Utilizing these AI capabilities can significantly enhance automation, improve data processing, and deliver intelligent insights directly within your custom ServiceNow applications.  
Learn about the AI capabilities available with ServiceNow Otto for App Engine that you can use to enhance custom applications.
There are several types of AI capabilities that you can add to custom applications:

* Skills
* AI agents
* Agentic workflows
{#ai-capabilities-with-now-assist-for-app-engine__ul_ayx_3t4_zfc}

The following sections describe what each capability is and how you can use it to enhance a custom application. To learn about which AI capability might be best for your custom application use case, see [Choosing the right AI capability](https://www.servicenow.com/docs/07tfwApdK4YwvH2QectFew "Choosing the right AI capability for your custom application is important. Learn about the differences between skills, AI agents, and agentic workflows, use cases for each, and when to choose one capability over another.").

## Skills {#ai-capabilities-with-now-assist-for-app-engine__section_ayl_mt4_zfc}

On the ServiceNow AI Platform, a skill is a generative AI capability that contains instruction on how to complete a specific task for a use case, such as generating a summary.  
There are several important components of a skill.

* The input is the data that the skill analyzes to generate an output. Typically on the ServiceNow AI Platform, inputs are records in tables.
* The prompt is the instruction to the underlying large language model (LLM) that tells the skill what to do with the input. Prompts define the task, tone, and structure of the output.
* The output is the generated response from the LLM based on the prompt and input. Outputs can be plain text, structured data, or even formatted responses depending on how the skill is configured.
{#ai-capabilities-with-now-assist-for-app-engine__ul_lxf_dzv_zfc}  
Skills also contain activation methods, which define how the skill can be accessed on the ServiceNow AI Platform. Skills can be called conversationally in the ServiceNow Otto® panel, through UI actions such as buttons, and through conversations with Virtual Agent. To learn more about activating skills, see [Activate a skill](https://www.servicenow.com/docs/access?context=activate-skill&version=australia&pubname=australia-intelligent-experiences&ft:locale=en-US).  
Note:  
Some skills might need to be reviewed and approved by a data steward before you can activate them. To learn more, see [Governing AI assets](https://www.servicenow.com/docs/access?context=aict-governing-ai-assets&version=australia&pubname=australia-intelligent-experiences&ft:locale=en-US).

## Platform skills vs. custom skills {#ai-capabilities-with-now-assist-for-app-engine__section_ypl_zzv_zfc}

With ServiceNow Otto for App Engine, you have access to several kinds of skills: Platform generative AI skills and custom skills. While you might be able to use both kinds of skills in custom applications, the following table provides more information about each skill type and the ease of using the skill in custom applications. {#ai-capabilities-with-now-assist-for-app-engine__table_o3m_tn4_xgc__entry__4}

| Skill type | Description | Ease of use in custom applications | More information |
|-|-|-|-|
| Platform generative AI skills | Preconfigured skills that are designed for existing use cases,such as document extraction and dashboard and visualization export | Must be duplicated and reconfigured significantly for use within custom apps | [Generative AI skills in the Platform workflow](https://www.servicenow.com/docs/access?context=now-assist-on-now-platform&version=australia&pubname=australia-intelligent-experiences&ft:locale=en-US) |
| Custom skills | Skills that you create custom for your use case with AI Skill Kit | Can be designed to work within custom apps during the creation process, when you define the skill inputs and outputs | * [General guidelines for AI Skill Kit](https://www.servicenow.com/docs/access?context=na-skill-kit-guidelines&version=australia&pubname=australia-intelligent-experiences&ft:locale=en-US) * [Create a skill](https://www.servicenow.com/docs/access?context=create-new-skill&version=australia&pubname=australia-intelligent-experiences&ft:locale=en-US) {#ai-capabilities-with-now-assist-for-app-engine__ul_hqj_wr4_xgc} |
[Table 1. Differences between Platform generative AI skills and custom skills]

{#ai-capabilities-with-now-assist-for-app-engine__table_o3m_tn4_xgc}

## ServiceNow Otto for App Engine custom app record summarization skill {#ai-capabilities-with-now-assist-for-app-engine__section_rc4_cr4_xgc}

Starting with version 28.2.4 of ServiceNow Otto for App Engine, you can use the custom app record summarization skill. The skill is a template skill available with ServiceNow Otto for App Engine that enables you to generate AI summaries of records within custom apps and tables. For more information, see [Custom app record summarization skill](https://www.servicenow.com/docs/xgjBISnq0cEoIXbRh8O7LA "The ServiceNow Otto for App Engine custom app record summarization skill can generate summaries for the contents of records in custom applications and tables.").

## AI agents {#ai-capabilities-with-now-assist-for-app-engine__section_w1f_nt4_zfc}

An AI agent is a generative AI capability that contains a set of large language model (LLM) instructions with the tools to perform specific tasks. On the ServiceNow AI Platform, AI agents are often part of agentic workflows and can be orchestrated to perform complex tasks. More information about agentic workflows is included in the following section.  
There are several important components of an AI agent.

* The AI Agent role defines the capabilities and responsibilities for the AI agent. Roles enable the AI agent to perform its required actions.
* The list of steps are the instructions are sent to the large language model (LLM) that describe the necessary steps the AI agent follows while carrying out its role.
* The tools are the additional resources, such as skills, and data sources that you can provide your AI agent to accomplish its role.
* The trigger defines how the AI agent is activated.
* The availability determines how your AI agent is displayed, either in the ServiceNow Otto® panel or Virtual Agent.

{#ai-capabilities-with-now-assist-for-app-engine__ul_oth_h2w_zfc}For more information about AI agents, see [AI Agent Studio overview](https://www.servicenow.com/docs/access?context=ai-agent-studio&version=australia&pubname=australia-intelligent-experiences&ft:locale=en-US).

## Agentic workflows {#ai-capabilities-with-now-assist-for-app-engine__section_jtq_5dw_zfc}

An agentic workflow contains a set of large language model (LLM) instructions with one or more AI agents that can execute an objective. Agentic workflows are tailored to achieve specific business outcomes, such as
classifying tasks or processing emails for tasks.

An agentic workflow is controlled by an AI Agent Orchestrator that coordinates the flow of work between AI agents. Additionally, an AI Agent Communicator helps to facilitate communication between the AI
Agent Orchestrator and AI agents in the workflow.

For more information about agentic workflows, see [General guidelines for creating AI agents and agentic workflows](https://www.servicenow.com/docs/access?context=gg-creating-aia&version=australia&pubname=australia-intelligent-experiences&ft:locale=en-US).

## Platform AI agents and agentic workflows vs. custom AI agents and agentic workflows {#ai-capabilities-with-now-assist-for-app-engine__section_gtz_lbw_zfc}

With ServiceNow Otto for App Engine, you enhance custom applications with Platform and custom AI agents and agentic workflows. Similar to adding generative AI skills, configuring Platform AI agents and agentic workflows to fit custom applications often takes more time than just building custom AI agents and agentic workflows from the start. The following table provides additional information about Platform and custom AI agents agentic workflows.{#ai-capabilities-with-now-assist-for-app-engine__table_ykz_ws4_xgc__entry__4}

|   |   | Ease of use within custom applications | More information |
|-|-|-|-|
| Platform AI agents and agentic workflows | Preconfigured AI agents and agentic workflows that are designed for existing use cases, such as incident resolution | Must be duplicated and modified significantly for use in custom applications | * [Explore AI agents](https://www.servicenow.com/docs/access?context=exploring-ai-agents&version=australia&pubname=australia-intelligent-experiences&ft:locale=en-US) * [Platform agentic workflows](https://www.servicenow.com/docs/access?context=platform-use-cases&version=australia&pubname=australia-intelligent-experiences&ft:locale=en-US) {#ai-capabilities-with-now-assist-for-app-engine__ul_p5t_lt4_xgc} |
| Custom AI agents and agentic workflows | AI agents that you create custom for your use case using AI Agent Studio | Can be designed to work within custom apps during the creation process, when you define the AI agent and agentic workflow | * [General guidelines for creating AI agents and agentic workflows](https://www.servicenow.com/docs/access?context=gg-creating-aia&version=australia&pubname=australia-intelligent-experiences&ft:locale=en-US) * [Create an AI agent](https://www.servicenow.com/docs/access?context=configure-next-best-action-agent&version=australia&pubname=australia-intelligent-experiences&ft:locale=en-US) * [Create an agentic workflow](https://www.servicenow.com/docs/access?context=configure-use-case-ai-agents&version=australia&pubname=australia-intelligent-experiences&ft:locale=en-US) {#ai-capabilities-with-now-assist-for-app-engine__ul_utn_1t4_xgc} |
[Table 2. Differences between Platform AI agents and agentic workflows vs. custom AI agents and agentic workflows]

{#ai-capabilities-with-now-assist-for-app-engine__table_ykz_ws4_xgc}