--- sourceDocument: Australia Enable AI sourceDocumentLink: https://www.servicenow.com/docs/r/australia/intelligent-experiences Release : - australia ft:locale : - en-US ft:publication_title : - Australia Enable AI ft:clusterId : - platai bundleId : - platai workflow : - Platform --- # GitHub code automation AI agent # GitHub code automation AI agent {#ariaid-title1} Release version: Australia Updated September 30, 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 GitHub code automation AI agent The GitHub code automation AI agent acts as an intelligent coding partner within GitHub repositories. It assists ServiceNow customers by clarifying coding requirements, proposing architectural approaches, generating or updating code in context, and managing commits and pull requests. This workflow ensures collaborative and controlled code changes with user approval at every step. Show full answer Show less ## Workflow * **Requirement Clarification:** The agent gathers detailed information on what the user intends to build or change, including the technology stack, and proposes an architecture for approval. * **Repository Context Setup:** It confirms repository ownership, repository name, and base branch, prompting the user for any missing details. * **Branch Management:** The agent lists existing branches and allows the user to select or create a new working branch derived from a base branch. * **Code Generation and Update:** It reviews repository structure, generates or updates relevant files, presents code snippets for user approval, and commits changes only upon approval. * **Pull Request Handling:** Upon completion of changes, the agent offers to create a pull request and confirms successful creation with the user. ## Configuration and Access Controls * **Third-Party Access:** By default disabled; when enabled, third-party AI agents can utilize this agent. * **AI Specialist Access:** Disabled by default; enabling this unlocks advanced configuration options for mapping inputs and response templates. * **Long-Term Memory:** Optional setting that allows the agent to use prior user interactions as contextual input for improved assistance. These configurations are managed via the AI Agent configs \[snaiaagentconfig\] table and system properties. ## Tools and Permissions * **Available Flow Actions:** Create Branch, Create Pull Request, Create or Update File, Look up Branches, Look up File Content, Repository Schema Fetcher. * **User Roles:** Access restricted to users with the `sncinternal` role. * **Data Access Roles:** Also limited to `sncinternal` roles, controlling accessible data and permissible actions. ## Integration and Usage This AI agent can be configured for use within Virtual Agent or ServiceNow Otto panels through Assistant Designer. It supports a guided, interactive coding experience but does not include default triggers or agentic workflows. Administrators can add triggers if desired to automate invocation. This AI agent acts as a coding partner for GitHub repositories. It clarifies requirements, proposes an approach, generates or updates code in context, and commits changes to a working branch and opens a pull request. ## Workflow {#inth-github-github-code-automation-agent-ai-agent__jkvxmwkpiwqk} The agent helps the user plan, write, and commit code changes to a GitHub repository. The user must provide approval at each step. 1. Clarify what the user wants to build or change, including the tech stack, and present a proposed architecture for the user to approve. 2. Confirm the repository owner, repository name, and base branch, asking the user for any that are missing. 3. List the repository's branches and let the user select an existing branch or create a new one from a base branch. 4. Review the repository structure and the files related to the change. 5. Generate or update each file, show the code to the user, and commit it to the working branch only after the user approves. 6. Ask whether there are more changes to make and, when the user is done, offer to create a pull request. 7. Create the pull request if requested and confirm completion with the user. {#inth-github-github-code-automation-agent-ai-agent__ol_fyd_ohv_baa} {#inth-github-github-code-automation-agent-ai-agent__jkvxmwkpiwqk__entry__2} | Field | Description | |-|-| | Allow third party to access this AI agent | When enabled, third-party AI agents can use this agent. This value is off (false) by default. This setting is defined in the AI Agent configs \[sn_aia_agent_config\] table on the External discoverable field. | | Allow AI specialists to access this AI agent | When enabled, AI specialists can use this agent. This value is off (false) by default. When set to true, more configuration options for tools become available so that an AI specialist can map inputs and response templates to tool outputs. This setting is defined in the AI Agent configs \[sn_aia_agent_config\] table on the Specialist enabled field. | | Manage long-term memory | When enabled, all previous user interactions are used as context for the LLM. This value is off (false) by default. This setting is defined by the sn_aia.ltm.enable_long_term_memory system property. For more information, see [ServiceNow Otto AI agents reference](https://www.servicenow.com/docs/MUqSU8rHp3ao~q3QEWgHkA "Find more information about user roles, tables, and the different properties that are installed in ServiceNow Otto AI agents."). | | Tools | Flow Actions : Create Branch : Create Pull Request : Create or update a File : Look up Branches : Look up File Content : Repository Schema Fetcher | | Allowed user roles The specific user roles that can access this AI agent. | snc_internal | | Data access roles The specific user identity roles that determine which data the AI agent can access and what actions it can take. | snc_internal | | Triggers | Optional. None defined by default. An admin can specify triggers if desired. For more information, see [Add a trigger to an AI agent](https://www.servicenow.com/docs/NXqRJBQV_Vw00FEzklcAJw "In the guided setup for an AI agent, add triggers to run the AI agent automatically when certain conditions are met."). | | Channels | Configure an assistant for Virtual Agent or ServiceNow Otto panel using [Assistant Designer](https://www.servicenow.com/docs/access?context=configure-now-assist-va&version=australia&pubname=australia-conversational-interfaces&ft:locale=en-US). | | Used in agentic workflows | Not applicable. | [Table 1. Configuration] **Related topics** * [GitHub Spoke](https://www.servicenow.com/docs/access?context=github-spoke&version=australia&pubname=australia-integrate-applications&ft:locale=en-US) * [Integration Hub spokes](https://www.servicenow.com/docs/access?context=spokes-list&version=australia&pubname=australia-integrate-applications&ft:locale=en-US)