Build Agent limitations

  • Release version: Zurich
  • Updated June 15, 2026
  • 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 Build Agent limitations

    Build Agent in the Zurich release helps ServiceNow customers plan deployments and troubleshoot issues by highlighting constraints that impact deployment capabilities and performance. It is designed to complement existing workflows rather than replace manual development steps. When Build Agent cannot perform specific actions, you should complete those tasks directly on the ServiceNow AI Platform® and then continue using Build Agent for the rest of your development process.

    Show full answer Show less

    Key Limitations

    • Human review required: AI-generated code must be reviewed for access control (ACL) correctness, security, platform conventions, and governance compliance. Implement peer-review gates, static checks, and validation steps accordingly.
    • Partial coverage of app files and metadata: Build Agent does not yet support all app files and metadata types, such as certain tables, UIs, or advanced features. Developers still need to use ServiceNow Studio for those components. However, Build Agent can enhance existing applications by creating business rules on existing tables.
    • Security scope: Security for apps developed with Build Agent applies at the application and API level by default, not at granular record or field levels. Agentic development can be used to build additional security layers through explicit requests.
    • Limited AI integration: Support for cross-product AI integration is limited. Build Agent can generate data models and business rules, but understanding where AI-generated app data resides on the ServiceNow AI Platform is important for proper management.
    • Dependency on ServiceNow Fluent: To fully understand Build Agent’s capabilities and limitations, familiarity with ServiceNow Fluent and its API reference is recommended. If no mapping exists between ServiceNow Fluent and XML metadata, Build Agent cannot update data without precise developer instructions.
    • Regulated environments: Build Agent v2 relies on off-instance services not yet certified for regulated hosting environments (e.g., GCC, NSC, FedRAMP). Customers in these environments must use Build Agent v1, which runs on-platform and is compliant. Alternatives in regulated environments include Developer Sandboxes, core update sets, Git workflows in Studio, Instance Scan, and ReleaseOps.

    Practical Guidance

    For troubleshooting issues, refer to the Build Agent’s documented “Issues and solutions.” For feedback or improvement suggestions, customers should use the Idea portal on Now Support. Understanding these limitations helps set realistic expectations and ensures effective use of Build Agent within your ServiceNow development lifecycle.

    Plan deployments and troubleshoot issues by learning about Build Agent constraints that affect deployment capabilities and performance.

    Troubleshooting

    If you encounter something that Build Agent can't currently do, complete that step directly on the ServiceNow AI Platform® and keep working with Build Agent for the rest of your development. Build Agent is designed to complement your workflow, not to replace it.

    For details on troubleshooting, see Issues and solutions in Build Agent.

    General limitations of Build Agent

    Be aware of the following limitations when using Build Agent:
    • AI-generated code requires human review for ACL correctness, security, platform conventions, and governance compliance. Put peer-review gates, static checks, and validation steps in place.
    • You still must work with builders in ServiceNow Studio for app files and metadata types not yet supported in Build Agent, such as certain tables, UIs, or advanced features.
      Note:
      Build Agent can work on existing applications. You can use Build Agent to enhance base workflows, such as creating business rules on existing tables.
    • Security in apps developed with Build Agent is at the application and API level, not at granular record and field level by default. However, you can use agentic development to build security onto the app by making requests. For examples, see Example prompts.
    • Limited support for cross-product AI integration.
    Build Agent can generate data models and business rules. You should understand where data from your AI-generated apps is stored on the ServiceNow AI Platform.

    Build Agent and ServiceNow Fluent

    To understand the upper limit of what Build Agent can do, review the ServiceNow Fluent documentation. If you're not familiar with the ServiceNow AI Platform, the ServiceNow Fluent documentation can help you determine what Build Agent can do. For more information, see the following topics:

    If there isn't a mapping between ServiceNow Fluent and the XML metadata, then Build Agent can't update the data unless you understand the platform well enough to precisely instruct Build Agent to make the changes you need.

    Regulated environments

    Build Agent and Test Agent depend on off-instance services that have not completed the security compliance review required for regulated hosting environments. As a result, Build Agent v2 (Australia Patch 0 and Zurich 8 and higher) is not available in GCC, NSC, or FedRAMP environments.

    Customers in regulated environments must remain on Build Agent v1, which runs on-platform and is certified for regulated use.

    In regulated environments where Build Agent v2 is unavailable, you can continue to use the following:

    • Developer Sandboxes
    • Core update set and Git workflows in ServiceNow Studio
    • Instance Scan
    • ReleaseOps

    Feedback on Build Agent

    To give feedback on Build Agent, see the Idea portal on Now Support.