Exploring Flow recommendations

  • Release version: Zurich
  • Updated August 7, 2025
  • 2 minutes to read
  • Summarize
    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 Exploring Flow recommendations

    ServiceNow’s Workflow Studio offers AI-generated flow recommendations to assist customers in selecting the next component when building flows. These recommendations are generated based on the current position in the flow and the names of previously added flow components, helping users design efficient workflows aligned with common patterns.

    Show full answer Show less

    Key Features

    • AI-Generated Suggestions: The system provides one to five recommended next steps in a flow using a generative AI model trained on internal ServiceNow flow patterns.
    • Scope of Recommendations: Suggestions include actions, flow logic, and subflows available within ServiceNow, excluding custom user-generated components or ServiceNow Store spokes.
    • Integration with Workflow Studio: Recommendations appear both in the diagramming view and text view at the end of the flow, ensuring consistent guidance during flow editing.
    • User Control: Customers can enable or disable flow recommendations per flow using the “Show recommendations” preference to tailor their authoring experience.

    Important Considerations

    • The AI model relies on pattern recognition and may not always provide fully accurate or complete recommendations.
    • Customers should rigorously test and validate AI-generated outputs to ensure correctness and appropriateness for their specific use cases.
    • Human oversight is strongly recommended, especially when flows impact critical domains like healthcare, finance, legal, security, or infrastructure.
    • Use of AI-generated recommendations must comply with ServiceNow’s AI Acceptable Use Policy.

    Practical Benefits for ServiceNow Customers

    By leveraging these AI-driven flow recommendations, customers can accelerate flow creation, reduce manual effort in decision-making, and follow proven design patterns within ServiceNow. This feature enhances productivity and helps ensure flows are logically structured, while allowing customization and control over the recommendation visibility.

    Select the next component in your flow from a list of AI-generated recommendations. The system generates recommendations based on the current position in the flow and the flow component names listed before.

    Figure 1. Example flow recommendations
    Five sample Flow recommendations for an empty flow

    The model uses the name of the flow components that come before to generate one to five recommendations for the next step of the flow. If there are no recommendations listed, then there are no flow components that meet the required relevance threshold.

    The system can only recommend actions, flow logic, and subflows that are available from ServiceNow. Recommendations can’t include user-generated flow components such as custom actions, nor can recommendations include actions from ServiceNow Store spokes.

    Generative AI model training

    This Generative AI large language model was pre-trained with internal ServiceNow flows to learn flow creation patterns. The goal was to understand what flow components are most relevant for a certain position in a flow given the content before.

    Flow preference

    Figure 2. Flow preferences
    Flow preference to show recommendations

    By default, Workflow Studio shows flow recommendations as you build a flow. You can hide these recommendations on a flow by flow basis by turning off the Show recommendations flow preference. See User preferences for flows for more information.

    Recommendations in diagramming view

    Workflow Studio shows recommendations from the flow diagramming view while you're editing a flow. In diagramming view, the last node of the flow always shows a list of recommendations. This experience matches the behavior of the text view, which also always shows a list of recommendations at the end of the flow.