---
sourceDocument: Australia Build or modify applications
sourceDocumentLink: https://www.servicenow.com/docs/r/australia/application-development

 Release :

    - australia

ft:locale :

    - en-US

ft:publication_title :

    - Australia Build or modify applications

ft:clusterId :

    - cadev

bundleId :

    - cadev

workflow :

    - Development, Data, and Analytics


---

# Overview

# Exploring Autonomous Engineer {#ariaid-title1}

Release version: Australia  
Updated October 19, 2026  
![](https://www.servicenow.com/docs/portal-asset/ico-clock) 2 minutes to read
Summarize  
![AI sparkle icon](https://servicenow.com/docs/portal-asset/ai-sparkle-icon) 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 Autonomous Engineer

Autonomous Engineer is an AI-driven agent designed to streamline and automate the implementation of applications on the ServiceNow AI Platform.
It transforms your application requirements into a structured implementation plan and then builds all work items in parallel using background agents.
The process consists of two main phases---planning and execution---both of which keep you in control with mandatory review and approval steps.
Show full answer Show less  
Available within ServiceNow Studio, Autonomous Engineer supports custom applications and leverages specialized agent packs containing product-specific domain knowledge to ensure accurate and efficient implementations.

## How It Works

* **Planning Phase:** You provide requirements via natural language prompts or file uploads (e.g., CSV user stories). Autonomous Engineer clarifies any ambiguities through an interactive interview, checks your instance for existing artifacts to avoid duplication, and produces a detailed plan with Agile user story--formatted work items sequenced by dependencies.
* You review, edit, and approve the plan before any build begins, ensuring full alignment with your needs.
* **Execution Phase:** Upon approval, Autonomous Engineer creates isolated background agents for each work item and builds them in parallel. It automatically generates Automated Test Framework (ATF) tests, runs them, and performs retries on failures with root cause analysis. Unresolved issues are flagged for your review.
* When all work items complete successfully, an update set is generated for deployment to testing or production environments.

## Manual Steps and Governance

Some implementation tasks, such as plugin activation, require manual intervention. Autonomous Engineer identifies these prerequisites in a manual verification section to minimize execution failures. Governance controls for Autonomous Engineer are managed through the Build Agent platform.

## Key Benefits

* Accelerates development by executing multiple work items in parallel.
* Automatically generates and manages ATF tests with retry logic to improve build reliability.
* Ensures correct build order through dependency sequencing of work items.
* Produces a consolidated update set for seamless deployment.
* Consolidates and clarifies complex requirements from various sources.

## Additional Features and Integration

* **Agent Packs:** Equip Autonomous Engineer with domain-specific knowledge and tools for accurate implementations.
* **Chat Panel:** Interactive interface for submitting requests, reviewing progress, running tests, and applying generated code.
* **Dashboard:** Visual status tracking of work items, milestones, and manual verification steps.
* **Resilience:** Automatic detection and retries for stuck or unresponsive build tasks.
* **Supported Models and Tools:** Compatibility with specific AI models and tools that enhance capabilities such as semantic search, schema inspection, and script execution.
* **MCP Connections:** Integration with external tools and third-party systems to enrich planning and implementation workflows.
* **Playbook Management:** Creation and configuration of Playbook Designer artifacts via conversational interaction without manual UI navigation.

## Practical Considerations

Autonomous Engineer relies on the Build Agent platform as its execution layer. Limitations applicable to Build Agent apply here as well, so customers should review those when planning implementations. Use the Plans view in Build Agent to manage and track all your Autonomous Engineer plans across sessions.  
Autonomous Engineer is an agentic worker that accepts requirements, generates a structured implementation plan, and builds all work items in parallel using background agents.

## Autonomous Engineer overview {#exploring-autonomous-engineer__cf-exploring-parent-overview}

Implementing applications on the ServiceNow AI Platform can require manual effort between defining requirements and building the application. Autonomous Engineer takes your specifications as input and drives the full implementation lifecycle end-to-end.

Autonomous Engineer follows two sequential phases: planning and execution. You remain in control throughout both phases. Autonomous Engineer requires your review and approval before building.

Autonomous Engineer is available in ServiceNow Studio and supports custom applications. Autonomous Engineer uses agent packs with product-specific domain knowledge to run implementations.

## How Autonomous Engineer works {#exploring-autonomous-engineer__cf-exploring-parent-how-it-works}

Planning phase

:   Provide your requirements in any of the following forms:

    * A natural language prompt or paragraph.
    * A file upload, such as a CSV of user stories.

    Autonomous Engineer reads your requirements and conducts an interview to resolve ambiguous or incomplete details. It queries your instance to identify existing artifacts and metadata such as tables, roles,
    fields, and catalog items, so existing artifacts aren't duplicated.

    The output of planning is a plan with work items. Work items are structured in an Agile user story format and include a description and acceptance criteria. They are grouped into logical sections and sequenced using a
    dependency graph so that each work item executes only after its dependencies are complete.

    Review every work item before execution begins. You can read the details, edit the content, and make changes to align the plan with your requirements. Nothing is built until you approve the plan and its work items.

Execution phase

:   After you approve the plan, Autonomous Engineer generates a background agent for each work item and builds all work items in parallel. Each agent runs in isolation. The plan dashboard displays the status of each work item as it
    progresses.

    For each work item, Autonomous Engineer builds the required metadata, runs Test Agent to generate Automated Test Framework (ATF) tests, and runs those tests. If tests fail, Autonomous Engineer identifies the root cause and attempts to resolve the failure through several retry cycles. Work items that can't be resolved automatically appear in the plan dashboard and the chat panel
    for your review.

    When all work items are complete, Autonomous Engineer generates an update set for the plan. Export the update set and deploy it for user acceptance testing or to a production environment.

    To view and manage all your plans across sessions, use the Plans view in the Build Agent navigator panel. For more information, see [Plans in Autonomous Engineer](https://www.servicenow.com/docs/B2D_~U_Y5COAkaCt1KJqUQ "Access all Autonomous Engineer plans from the Plans view in the Build Agent panel. The Plans view shows the plans you created and all plans available on the instance.").

## Manual steps {#exploring-autonomous-engineer__cf-exploring-parent-manual-steps}

Some implementation tasks fall outside what Autonomous Engineer can perform autonomously, such as activating plugins. When a plan includes steps that require manual action, Autonomous Engineer lists those steps in a manual verification section before you run the plan. Completing manual steps before execution reduces the risk of work items failing because of missing dependencies.

## Autonomous Engineer benefits {#exploring-autonomous-engineer__cf-exploring-parent-benefits}

Autonomous Engineer supports application development on the ServiceNow AI Platform in the following ways:

* Parallel execution of work items.
* Automatic ATF test generation and retry cycles for failed tests.
* Structured planning with dependency sequencing so artifacts are built in the correct order.
* A single update set output, ready for deployment to test or production environments.
* Consolidation of requirements across multiple sources and systems.
* Clarification and validation of complex requirements.

## What to explore next {#exploring-autonomous-engineer__cf-exploring-parent-links}

For more information about configuring and using Autonomous Engineer, see:

* [Configure Autonomous Engineer](https://www.servicenow.com/docs/G1fvwe8dhS059DHdvmKZ0g "Configure Autonomous Engineer by installing it from the ServiceNow Store and enabling the features required for planning and parallel execution on your instance.")
* [Using Autonomous Engineer](https://www.servicenow.com/docs/rr7kvJWwRUSxAQJjxc_HZg "Use Autonomous Engineer to provide requirements, review an implementation plan, and build all work items in parallel using background agents in Build Agent.")
* [Autonomous Engineer reference](https://www.servicenow.com/docs/Fd~mQToEkYxvOdSyevDLaA "Reference information for Autonomous Engineer, including work item states, agent packs, and supported capabilities in Build Agent.")
* **[Autonomous Engineer and Build Agent](https://www.servicenow.com/docs/N9A8duJdpREfEEaU3HeFNQ)**   
  Autonomous Engineer and Build Agent are separate products that work together. Autonomous Engineer uses Build Agent as its execution layer.
* **[Agent packs for Autonomous Engineer](https://www.servicenow.com/docs/VUhZDlOs4txto~fXXNDtHg)**   
  Agent packs bundle the domain knowledge, tools, and skills that Autonomous Engineer uses to implement ServiceNow products.
* **[Autonomous Engineer chat panel](https://www.servicenow.com/docs/WSTHwX46blgghfdbvjB1aA)**   
  The Autonomous Engineer chat panel within Build Agent is where you interact with the AI agent during planning and development. Use it to submit requests, review responses, run tests, and apply generated code.
* **[Using the dashboard](https://www.servicenow.com/docs/tD5bebZqC7BAMk~qJwEg4Q)**   
  The Autonomous Engineer dashboard displays the status of every work item in your plan and provides navigation to individual work items, milestones, and pre-flight verification items.
* **[Resilience in Autonomous Engineer](https://www.servicenow.com/docs/XChgdgf___5VXEiy9rhA1A)**   
  Autonomous Engineer monitors background agents during execution and automatically detects and retries work items that get stuck or unresponsive.
* **[Supported models for Autonomous Engineer](https://www.servicenow.com/docs/1xFoLYWJ0s6OxXBmqozzMQ)**   
  Learn which AI models and versions Autonomous Engineer supports and how to change them. Use this information to verify compatibility and select the right model for your task.
* **[Supported tools for Autonomous Engineer](https://www.servicenow.com/docs/peazO2A1FhkZyFmAankj4g)**   
  Autonomous Engineer tools support application development tasks such as semantic search, schema inspection, code search, planning, UI validation, database querying, app navigation, and script execution. Each tool extends what Autonomous Engineer can do during a build session.
* **[MCP connections and Autonomous Engineer](https://www.servicenow.com/docs/4aqp5U38lUluPPS7Q51dnA)**   
  MCP connections enable Autonomous Engineer to access external tools and resources through standardized communication, extending the planning and implementation workflow with data and context from third-party systems.
* **[Playbooks in Autonomous Engineer](https://www.servicenow.com/docs/qOsg03FWhnpqGnpzkjf4SQ)**   
  Use Autonomous Engineer to author and manage Playbook Designer artifacts through a conversation. You can generate playbook structures, configure activities, set runtime permissions, and define launcher configurations without manually navigating the Playbook Designer UI.
* **[Autonomous Engineer governance](https://www.servicenow.com/docs/bHaojtXN_vVF6g0aqC9~2g)**   
  Governance controls for Autonomous Engineer are managed through Build Agent.
* **[Autonomous Engineer limitations](https://www.servicenow.com/docs/isqzxmjHi0lrMs2MGfkEeg)**   
  Limitations that apply to Build Agent also apply to Autonomous Engineer.