Build Agent governance

  • Release version: Zurich
  • Updated July 24, 2026
  • 4 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 governance

    Build Agent governance in ServiceNow ensures that AI-generated applications meet enterprise standards for code quality, security, and compliance. It integrates with AI Control Tower and App Engine Management Center to provide comprehensive lifecycle management, identity framework consistency, and policy enforcement for apps and AI agents created using Build Agent.

    Show full answer Show less

    Governance Capabilities

    • Risk and Compliance: Ensures AI-generated apps adhere to security standards and regulatory requirements.
    • Quality Assurance: Validates automated code through testing, review, and optimization before publishing.
    • Visibility and Control: Prevents shadow IT, enforces lifecycle transparency, and provides audit trails for generated apps.

    Security Controls and Access Management

    Build Agent automatically generates Access Control Lists (ACLs) and supports the full suite of ServiceNow security controls including:

    • Security Attributes: Attribute-based access control that governs access based on user and resource properties rather than roles alone.
    • Security Data Filters: Row-level data restrictions, for example, allowing managers to see only their team’s records.
    • Cross-Scope Privileges: Controls access between scoped applications and helps resolve cross-scope operation errors.

    Build Agent validates scripts for security vulnerabilities and applies code optimization to maintain secure and efficient code generation.

    Lifecycle Monitoring and Risk Management

    Agents generated by Build Agent are registered as AI assets in AI Control Tower where AI stewards can:

    • Track lifecycle progression and monitor security posture.
    • Assess compliance and review governance health and risk classification.
    • Identify agents with elevated permissions, access errors, or inactivity with active permissions.
    • Visualize dependencies via access maps to evaluate potential impacts before changes.

    If your organization uses AI Risk and Compliance, generated agents can be assessed against frameworks such as NIST AI Risk Management Framework and the EU Artificial Intelligence Act.

    Operational Safeguards for Script Execution

    • Approval Before Execution: Every script run requires user approval after reviewing the script, intent, and application scope.
    • Scope Restriction: Scripts run within the app’s scope or a specified scope; failure to resolve scope names prevents execution.
    • On-Demand Rollback: Scripts run by Build Agent can be reverted with an approval step to undo changes if needed.

    Custom Skills and Rules

    Administrators can define custom skills and rules to enforce organizational standards and guide Build Agent behavior. Rules apply automatically to sessions at the configured scope, while skills provide on-demand guidance during development.

    Practical Benefits for ServiceNow Customers

    • Ensures generated applications comply with enterprise security and regulatory policies without manual intervention.
    • Reduces risk of security vulnerabilities through automated validation and governance controls.
    • Provides transparency and control over AI-generated app lifecycle and access permissions.
    • Facilitates troubleshooting of scoped app access issues via Cross-Scope Privileges.
    • Enables safe script execution with approval and rollback capabilities to protect system integrity.
    • Supports continuous governance through integration with AI Control Tower and AI Risk and Compliance frameworks.

    Governance controls in Build Agent help with code quality, security, and compliance when generating applications. The Build Agent automated safeguards prevent common development issues and enforce organizational standards.

    Every app and AI agent generated with Build Agent inherits the governance of AI Control Tower and App Engine Management Center, plus the same identity framework as the rest of the ServiceNow AI Platform®. Use the governance tools to monitor agents, manage app lifecycle, and enforce policy.

    Governance addresses the following:
    • Risk and compliance: AI-generated apps meet enterprise security standards and regulatory requirements.
    • Quality assurance: Automated code is validated through testing and review.
    • Visibility and control: Prevents shadow IT and enforces lifecycle transparency.

    Build Agent automatically generates Access Control Lists (ACLs) that enforce role-based access, validates scripts for security vulnerabilities, and applies code optimization during generation. Every app that's developed agentically on the ServiceNow AI Platform includes audit trails, security controls, and compliance checks without requiring explicit prompts for these features.

    Build Agent supports the full set of native ServiceNow security controls, not only ACLs and roles. For example, Build Agent can create Security Attributes for attribute-based access control and Security Data Filters for row-level data restriction.
    • Security Attributes control access based on properties assigned to users and resources, instead of role membership alone. For more information on Security Attributes, see Security Attributes.
    • Security Data Filters restrict which rows a user can see on a table, for example, so that managers see only their team's records.
    All four security metadata types can be combined in a single application for layered access control.
    Some ways that Build Agent enforces governance include:
    • Enforce ACLs and role-based access for generated apps, which Build Agent can do.
    • Validate AI-generated scripts for security vulnerabilities.
    • Apply code optimization and review before publishing.
    • Create Cross-Scope Privileges to control which tables, scripts, and resources one scoped application can access from another. Use Cross-Scope Privileges to diagnose and resolve operation not allowed errors between scoped apps.
    • While creating agents and skills, Build Agent asks which users and roles it should operate as, as well as which users are allowed to access the agents or skills.

    AI Control Tower

    Agents generated by Build Agent are registered as AI assets in AI Control Tower, where AI stewards can track lifecycle progression, monitor security posture, and assess compliance. From the AI asset record, stewards can review governance health, evaluation scores, and risk classification for each agent without leaving the workspace.

    AI Control Tower identifies specific security considerations for generated agents, including the following:
    • Agents with elevated permissions
    • Agents that experience access-related errors
    • Agents that have been inactive for more than 90 days but still retain active permissions
    The access map visualizes relationships between agents, agentic workflows, and the tools they use, which helps stewards assess dependencies and potential impact before making changes.

    If your organization uses AI Risk and Compliance, generated agents can be evaluated against organizational policies and regulatory frameworks. For example, the NIST AI Risk Management Framework and the EU Artificial Intelligence Act. Risk classification and compliance posture are surfaced on the Risk and Compliance tab of each AI asset record.

    For more information, see AI Control Tower (legacy).

    For more information on governance, agentic development and other ServiceNow development tools, see Governance for agentic development.

    Cross-scope privileges

    Build Agent can create Cross-Scope Privilege records to control which tables, scripts, and resources one scoped application can access from another. If a scoped app needs to read a table or call a script include from a different scope, Build Agent generates the appropriate privilege records. Cross-Scope Privileges are also useful for diagnosing and resolving operation not allowed errors between scoped apps.

    Background script containment

    When Build Agent runs a background script using one of the script tools, several containment controls limit the impact of server-side execution.

    Approval before execution
    Build Agent requires you to approve every script run before it executes. The approval prompt shows the generated script, its stated intent, and the target application scope so you can review the operation before it runs.
    Scope restriction
    Scripts run in the scope of the app being built by default. You can specify a different scope by name. If the scope name can't be resolved, the run fails rather than executing in the global scope.
    On-demand rollback
    After a script runs, Build Agent returns a rollback context you can use to revert the operation. Rollback requires the same approval step as the original run. Only scripts run by Build Agent can be reverted using this mechanism.

    For more information on using the script tools, see Build Agent tools.

    Custom skills and rules

    Admins can define custom skills and rules to enforce organizational standards and guide Build Agent behavior across sessions. Rules apply automatically to every session at the configured scope. Skills provide on-demand guidance that Build Agent can draw on when needed.

    For more information, see Configure custom skills and rules.