Explore flow execution analysis
Summarize
Summary of Explore flow execution analysis
The Explore flow execution analysis feature helps ServiceNow customers summarize flow execution details and receive AI-driven recommendations to resolve flow errors. This capability is part of the ServiceNow Otto for Creator (snnowcreator) application, which can be installed from the ServiceNow Store.
Show less
Key Features
- Flow execution summarization: Provides concise summaries of flow execution details even when flow reporting is disabled.
- Error identification and resolution: Detects potential causes of flow errors and offers suggested fixes using generative AI.
- Supported AI models: Compatible with multiple large language models (LLMs) including Now LLM Service, Azure OpenAI, Google Gemini, and Anthropic Claude on AWS. Configuration of available AI options and preferences is managed via AI Control Tower and AI Admin Hub.
- Flow analysis interface: Accessible from the Workflow Studio sidebar, users can generate flow execution analyses, view root cause analyses, and explore potential fixes. New flows show an “Analyze flow” button; existing analyses display their creation dates.
- Flow reporting requirements: Flow execution analysis depends on flow execution details. With flow reporting on, any flow can be analyzed. With flow reporting off, analysis is limited to flows in error states using flow context records.
Important Considerations
- This feature leverages AI and machine learning, which may not always provide fully accurate or complete recommendations.
- Customers should rigorously test and evaluate AI-generated outputs for accuracy and appropriateness before applying them to critical decisions.
- Human oversight is essential, especially in sensitive areas such as healthcare, finance, legal, employment, security, and infrastructure.
- Use of this feature must comply with ServiceNow’s AI Acceptable Use Policy.
What ServiceNow Customers Can Expect
By enabling flow execution analysis, customers gain enhanced visibility into flow operations and faster troubleshooting through AI-assisted insights. This improves flow reliability by helping to quickly identify and resolve errors with recommended fixes, even when traditional flow reporting is disabled.
Summarize flow execution details and get recommendations to resolve errors with generative AI.
Activation
The flow summarization skill is installed with the ServiceNow Otto for Creator (sn_now_creator) application. You can install this application from the ServiceNow Store website.
Benefits
- Summarize flow execution details when flow reporting is off.
- Identify potential causes of flow errors.
- Resolve flow errors with suggested fixes.
Supported LLMs
You can use Now LLM Service, Azure OpenAI, Google Gemini or Anthropic Claude on AWS as the AI model provider for all generative AI skills and AI agents. Use the Configuration Controls in AI Control Tower to define which options are available, then set the skill-level preferences in the AI Admin Hub console. For more information, see Large language models on the ServiceNow AI Platform®.
Flow analysis
You can generate and view a flow execution analysis from the Workflow Studio sidebar.
From the Analysis sidebar, you can generate an analysis of the flow execution details. A flow that has never been analyzed displays a Analyze flow button.
An existing flow analysis lists its creation date.
The Root Cause Analysis and Potential Fixes sections contain information and suggestions to potentially improve your flow.
Flow reporting requirements
Flow execution analysis requires flow execution details to analyze. When flow reporting is on, you can analyze any flow using information from its flow execution details. When flow reporting is off, you can only analyze flows that are in an error state using information from the flow context record. For more information about setting flow reporting, see Activate flow reporting.
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.