Workflow for agentic development

  • Release version: Australia
  • Updated June 5, 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 Workflow for agentic development

    Agentic development in ServiceNow enables developers to build applications using AI-assisted tools such as Build Agent and Now Assist for Creator. This workflow supports creating tables, forms, workflows, and automation rules through conversational prompts, with integrated governance and enterprise-grade security throughout the process. It accommodates different approaches—from fully automated deployment without code review to iterative, conversational app refinement where developers maintain control and oversight.

    Show full answer Show less

    Step-by-step Workflow

    • Describe your goal: Provide a clear, detailed natural language prompt describing the desired application, including context such as roles, data needs, and success criteria. This initial step ensures robust and accurate app creation.
    • Generate the plan: Build Agent translates your prompt into a blueprint encompassing tables, roles, UI components, and workflows, giving architectural clarity before coding begins.
    • Build and generate code: ServiceNow AI Platform autonomously creates full-stack app components—UI pages, data models, business rules, and integrations—using ServiceNow Fluent, JavaScript, and metadata.
    • Validate and self-heal: Automated tests are generated and errors are fixed without manual effort. Compliance, security, and governance checks are automatically applied to ensure enterprise standards.
    • Refine through prompts: Iteratively enhance or adjust features and design by providing additional prompts (e.g., adding UI elements or improving accessibility).
    • Run tests: Use the Automated Test Framework to verify the app functions as expected.
    • Deploy securely: Deploy from Developer Sandboxes with audit trails and enterprise-grade security controls including Vault Console and Machine Identity Console.

    Key Outcomes

    • Rapid, AI-powered application creation guided by natural language prompts.
    • Architectural transparency and governance embedded to meet enterprise compliance and security standards.
    • Iterative development enabling developers to maintain control and refine AI-generated apps.
    • Automated validation and error correction to enhance app quality and reliability.
    • Secure deployment with full audit trails supporting enterprise governance requirements.

    The agentic development workflow begins with developers providing conversational prompts to the Build Agent tool, which then creates tables, forms, workflows, and automation rules.

    Integrated tools like Build Agent and Now Assist for Creator enhance the experience by offering text-to-code generation, code explanations, and optimization suggestions. Governance and security are embedded throughout the process, ensuring enterprise-grade compliance and scalability.

    Note:
    Agentic development encompasses a range of approaches to AI-assisted app building:
    • In one approach, developers provide a goal and deploy the generated output without reviewing the underlying code.
    • In another approach, agentic development is an iterative, conversational process in which developers guide AI generation, review the output, and retain responsibility for the generated code.
    ServiceNow provides tools to help you review, refine, and test apps throughout agentic development, including Build Agent and Now Assist for Creator.

    Step-by-step general workflow

    1. Describe your goal: Provide a clear natural language prompt (for example, Create an application that handles several types of issues related to cash management. Create a custom data model with tables for each type of request. Add fields that are typical for these types of issues to each table. Request tables should extend the Task table. Create custom states for each request type to track issue resolution.).

      Tip:
      • If you're using Build Agent, include as much context as possible in your first prompt to enable more robust development. Include roles, data requirements, and success criteria.
      • You can craft a prompt and then feed it to an LLM, such as Claude, and ask for it to be made more specific for ServiceNow.

      For more information on example prompts, see Example prompts for vibe coding and AI-assisted development.

    2. Generate the plan: Build Agent interprets your prompt and creates a blueprint, including tables, roles, UI components, and workflows.

      Benefit: Architectural clarity before coding begins. For more information, see Vibe coding: Chatting your way to a new app with ServiceNow Build Agent.

    3. Build and generate code: The ServiceNow AI Platform autonomously creates full-stack components using ServiceNow Fluent, JavaScript, and ServiceNow metadata.

      Includes: UI pages, data models, business rules, and integration points. For more information, see Vibe coding with ServiceNow Build Agent: The future of AI-powered app development.

    4. Validate and self-heal: If you're using Build Agent, it generates automated tests and fixes errors without manual intervention.

      Governance: Compliance and security checks are applied automatically. For more information, see Governance for agentic development.

    5. Refine through prompts: Add features or adjust design iteratively (for example, Add a Kanban board or Improve UI layout for accessibility).

      For more information, see Vibe Coding: Chatting your way to a new app with ServiceNow Build Agent on Community.

    6. Run tests: Run Automated Test Framework to test that the app is working as expected.

      For more information, see Testing agentically developed apps.

    7. Deploy securely: Push from a sandbox in Developer Sandboxes with audit trails and enterprise-grade security via Vault Console and Machine Identity Console.

      For more information, see Agentic development and deployment.