Explore flow execution analysis
Summarize flow execution details and get recommendations to resolve errors with generative AI.
Activation
The flow summarization skill is installed with the Now Assist 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, Now LLM Long Term Stable models (LTS), Azure OpenAI, Google Gemini or Anthropic Claude on AWS as the AI model provider for all Now Assist 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 Now Assist Admin 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.
You can regenerate a flow execution analysis from the Analysis sidebar.
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.