Flow summarization
Summarize
Summary of Flow summarization
Flow summarization in ServiceNow uses generative AI to provide concise summaries of what a flow or subflow does. This capability helps customers quickly understand and communicate the purpose and function of automation workflows within their ServiceNow environment.
Show less
Key Features
- Generative AI Integration: Utilizes AI to automatically generate clear summaries of flows or subflows.
- Flow Summarization Skill: Requires activation of the ServiceNow Otto for Creator plugin and enabling the flow summarization skill to use this feature.
- Default Behavior: For new customers, relevant AI skills and agents are automatically enabled upon installation. Existing customers upgrading from Zurich Patch 4 retain their current AI settings unless changed by an admin.
Important Considerations
- Availability Restrictions: Some AI features and model providers are not available in certain regions, data centers (including FedRAMP, NSC DOD IL5, Australia IRAP-Protected), self-hosted environments, or regulated markets. Customers should verify availability for their specific environment and region.
- AI Limitations: AI-generated summaries may not always be fully accurate or appropriate. Customers are responsible for validating outputs and employing human oversight, especially in sensitive or consequential areas such as healthcare, finance, or security.
- Data Processing: Using flow summarization involves transferring data from customer instances to centralized ServiceNow environments and potentially third-party cloud providers like Microsoft Azure, managed according to ServiceNow’s compliance policies.
Next Steps for Customers
- Activate the ServiceNow Otto for Creator plugin.
- Enable the flow summarization skill to start generating flow descriptions.
- Review AI feature availability and compliance requirements relevant to your environment.
- Implement appropriate human oversight and testing to ensure AI-generated summaries meet your accuracy and governance standards.
Summarize what a flow or subflow does by using generative AI.
Get started
|
Configure |
|
|
Reference |
- Not all model providers are available for customers with in-country SKUs, and some AI products/features are currently unavailable for in-country customers. For more information, see the KB1584492 article in the Now Support Knowledge Base. Be sure to check for model provider availability updates in future releases.
- Some AI products/features are currently unavailable for customers in the FedRAMP, NSC DOD IL5, or Australia IRAP-Protected data centers, self-hosted customers, or in other restricted environments. For more information, see the KB0743854 article in the Now Support Knowledge Base. Be sure to check for availability updates in future releases.
- Some AI products/features are currently available only for customers in some regions. Be sure to check for availability updates in future releases.
- Some AI products and skills are not available in Regulated Markets. For more information, see KB2593939: Regulated Markets AI Products/Skills Not Available. Be sure to check for availability updates in future releases.
- New customers
- When you install an AI product, designated generative AI skills, AI agents, or agentic workflows are turned on automatically.
- Existing customers who are upgrading (starting with Zurich Patch 4)
- There is no change to skills, agents, or agentic workflows that are currently enabled and customized.
An AI asset is turned on if:
- The AI plugin is installed, but the asset was never turned on.
- An admin has never adjusted roles for the skill.
An AI asset is not turned on if:- The asset was previously turned on, and then turned off again.
- An admin has adjusted roles for the asset.
AI limitations
This application uses artificial intelligence (AI) and machine learning, which are rapidly evolving fields of study that generate predictions based on patterns in data. As a result, this application may not always produce accurate, complete, or appropriate information. Furthermore, there is no guarantee that this application has been fully trained or tested for your use case. To mitigate these issues, it is your responsibility to test and evaluate your use of this application for accuracy, harm, and appropriateness for your use case, employ human oversight of output, and refrain from relying solely on AI-generated outputs for decision-making purposes. This is especially important if you choose to deploy this application in areas with consequential impacts such as healthcare, finance, legal, employment, security, or infrastructure. You agree to abide by ServiceNow’s AI Acceptable Use Policy, which may be updated by ServiceNow.
Data processing
This application requires data to be transferred from ServiceNow customers' individual instances to a centralized ServiceNow environment, which may be located in a different data center region from the one where your instance is, and potentially to a third-party cloud provider, such as Microsoft Azure. This data is handled per ServiceNow's internal policies and procedures, including our policies available through our CORE Compliance Portal.