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

 Release :

    - brazil

ft:locale :

    - en-US

ft:publication_title :

    - Brazil Build or modify applications

ft:clusterId :

    - cadev

bundleId :

    - cadev

workflow :

    - Development, Data, and Analytics


---

# Autonomous Engineer

# Autonomous Engineer in Build Agent {#ariaid-title1}

Release version: Brazil  
Updated September 10, 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 Autonomous Engineer in Build Agent

Autonomous Engineer is an advanced feature within the Build Agent designed to automate the full implementation lifecycle of custom applications in ServiceNow Studio.
Instead of manually building each artifact through conversational prompts, Autonomous Engineer takes your requirements as input and generates a comprehensive implementation plan.
It then executes the work items in parallel, significantly speeding up the build process for large or complex applications.
Show full answer Show less  
To use Autonomous Engineer, you must install the app from the ServiceNow Store and verify your entitlements. It is intended for customers with well-defined requirements who want to streamline their application builds.

## Process

The Autonomous Engineer workflow consists of two main phases, with customer control maintained throughout:

* **Planning Phase:** You provide requirements either as natural language descriptions or file uploads, such as CSVs containing user stories. Autonomous Engineer clarifies ambiguous details by interviewing you and checks your instance to avoid duplicating existing tables, roles, or fields. It then produces a detailed plan with work items structured as Agile user stories, including acceptance and test criteria, arranged via a dependency graph. You review and can edit the plan before approval.
* **Execution Phase:** After plan approval, Autonomous Engineer generates background agents for each work item and builds them concurrently. These agents create the required artifacts, generate Automated Test Framework (ATF) tests, execute these tests, and handle failures with automatic root cause analysis and retries. Once all work items are complete, an update set is generated for deployment.

## Key Features

* **Parallel Execution:** Builds multiple work items simultaneously, reducing build time for complex applications.
* **Automated Testing and Fault Handling:** Generates and runs ATF tests with automatic fault analysis and retry mechanisms to ensure quality.
* **Agent Packs:** Utilizes product-specific agent packs to equip background agents with domain knowledge for precise implementation.
* **Planning and Review Control:** You retain control by reviewing and approving the implementation plan before execution begins.

## Comparison to Standard Build Agent Development

Standard Build Agent development is a conversational, step-by-step process where you guide and review each artifact individually. Autonomous Engineer, in contrast, creates and executes an end-to-end plan, minimizing manual prompting and interaction during the build.

Use **Standard Build Agent** for incremental builds, exploratory changes, or targeted updates. Use **Autonomous Engineer** when you have comprehensive requirements and want to accelerate the build process with minimal manual intervention.  
Autonomous Engineer is an agentic worker in Build Agent that takes your requirements and generates an implementation plan. It then builds all work items in parallel, without requiring you to construct each artifact manually.
When an application is large or complex, building it artifact-by-artifact through conversational prompts can be slow. Autonomous Engineer addresses this by taking your requirements as input and driving the full implementation lifecycle end to end, from requirements intake through parallel execution of work items.  
Note:  
You must install the Autonomous Engineer app from the ServiceNow Store. Check your entitlements to see whether you can use Autonomous Engineer.

Autonomous Engineer is available in ServiceNow Studio and covers custom applications. For full product documentation, see [Autonomous Engineer in Build Agent](https://www.servicenow.com/docs/i_WthpSahFPirKQRxJitcQ "Autonomous Engineer is an agentic worker that augments product development capacity across the SDLC. It intakes requirements, applies platform best practices through agent packs, and generates an implementation plan before building work items in parallel through Build Agent.").

## Autonomous Engineer process {#vc-autonomous-engineer__section_ae_how_it_works}

Autonomous Engineer follows two sequential phases. You retain control throughout both phases and must review and approve the plan before any artifacts are built.

Planning phase
:   Provide your requirements as a natural language description or a file upload, such as a CSV of user stories. Autonomous Engineer interviews you to resolve ambiguous details. It then queries your instance to identify existing tables, roles, fields, and catalog items so it does not duplicate what is already there. The
    output is a plan with work items structured in an Agile user story format, including acceptance criteria and test criteria, sequenced using a dependency graph. Review and edit each work item before approving the plan.

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 builds the required artifacts, generates Automated Test Framework (ATF) tests, and runs those tests. Failed tests trigger automatic root cause analysis and retry cycles. When all work items are complete, Autonomous Engineer generates an update set for deployment.

## Agent packs {#vc-autonomous-engineer__section_ae_agent_packs}

Autonomous Engineer uses agent packs to give background agents product-specific domain knowledge during implementation. For more information, see [Agent packs for Autonomous Engineer](https://www.servicenow.com/docs/nKSBokCvc7ZtJJYN7pmfnA "Agent packs bundle the domain knowledge, tools, and skills that Autonomous Engineer uses to implement ServiceNow products.").

## Autonomous Engineer compared to standard Build Agent development {#vc-autonomous-engineer__section_ae_difference}

Standard Build Agent development is conversational and turn-by-turn: you prompt, review, and iterate on one artifact or change at a time. Autonomous Engineer shifts that model by working from a plan. It builds multiple work items in parallel in the background, so you interact primarily at the planning and review stages rather than guiding every step.

Use standard Build Agent development when you're building incrementally, exploring ideas, or making targeted changes. Use Autonomous Engineer when you have well-defined requirements for a larger implementation and need to reduce the number of manual prompting steps.

