AI Agent: Maintenance Work Order Builder

Agent Name

Maintenance Work Order Builder

Agent Use Case 

Maintenance teams need a more efficient and reliable way to create, modify, and access work order data without navigating complex screens or relying on fragmented inputs. The Maintenance Work Order Builder AI agent enables users to manage and interact with maintenance work order records through a conversational experience. The new agent template is available to help maintenance users create, update, or retrieve maintenance work orders without navigating to the user interface.

The Maintenance Work Order Builder agent template allows users to create new work orders with or without operations. When creating a work order, users can specify fields such as asset number, work order type, subtype, priority, description, and planned start date. A standard or ad-hoc operation can be added at the time of creation, or the work order header is created with no operations. For standard operations, users must enter in the standard operations code. To create work orders with work definitions, users must enter in the work definition code. When creating a new work order the user must provide the organization in which the work order is to be created.

To update an existing work order, the agent requires that users provide the work order number (WorkOrderNumber) and clearly specify the fields they wish to update in the work order header fields such as priority or planned start date. When updating work order operations, the agent only supports edits at the work order operation level, including operation description.

Users can also retrieve information about existing work orders. By entering a single work order number, the agent returns full details such as description, work order status, planned and actual dates, and operations. Additionally, users can retrieve a list of multiple work orders by specifying criteria such as date range, asset, or status. The agent returns a structured summary of matching work orders that can help maintenance teams monitor work order activity.

It's important that the information the users enter in the correct format and sequence. Field names always come before their values. If values contain spaces or special characters, they must be enclosed in double quotes. For example, "Create a work order for asset ‘Pump A1’ with type corrective, subtype emergency, and a priority of 1.”

When prompted for missing information, users need to rephrase their entire request with the new detail included. The agent does not retain memory of prior message fragments in updates, so resending the full instruction ensures the process completes correctly.

Only supported fields and actions need to be used. While the agent allows creation and update of work orders, it doesn't support adding or modifying material or resource transactions. Attempts to perform unsupported actions result in a clarification prompt or an error message.

If users experience unexpected results such as incorrect values returned or work orders not being found, it's recommended to clear the session context and restart the agent. This ensures that the request is evaluated by the agent without interference from prior messages. It's recommended to perform only one work order transaction per session.

Agent Description

The Maintenance Work Order Builder Agent streamlines the creation, retrieval, and updating of maintenance work orders within Oracle SCM. The agent supports the following core functions:

  • Retrieve Work Order Details: Given search criteria or a work order number, the agent fetches comprehensive details such as description, priority, key dates, operations, and related data.
  • Create Maintenance Work Orders: The agent creates new maintenance work orders using provided data, with or without associated operations, or from a work definition.
  • Update Existing Work Orders: The agent updates work order header fields and operations, enabling efficient management throughout the work order lifecycle.

This tool enhances efficiency and accuracy in managing maintenance work orders, supporting operational needs and integration requirements.

Agent Tools 

Tool Name

Tool Code

Tool Type

Tool Description

Maintenance Work Order Tool

ORA_MNT_WO_TOOL

Business Object

This tool supports functions to retrieve and manipulate maintenance work orders. This tool can help with following requirements: - To quickly create new maintenance work orders with the right details for your organization and assets. - To retrieve comprehensive information or status updates on any existing work order for reporting, auditing, or operational action. - To make updates or adjustments to open work orders, such as revising schedules, adding new operational steps, or closing completed tasks.

Edit Work Order DeepLink Tool

ORA_SCM_MNT_EDIT_WO_DEEPLINK_TOOL

Deep Link

Link for Maintenance Supervision Workbench edit/view work order

Maintenance Asset Tool

ORA_SCM_MNT_MAINTENANCE_ASSET_TOOL

Business Object

Use this tool to retrieve key details for a specified asset. Given an Asset Number, the tool returns fields such as AssetId, ItemNumber, ItemId, default work order type, default work order subtype, and default work center code. This supports streamlined asset management and maintenance planning.

Maintenance Work Definition Tool

ORA_SCM_MNT_SRCH_WORK_DEFINITION_TOOL

Business Object

Use this tool to retrieve comprehensive details about a maintenance work definition within Oracle Fusion Maintenance. By specifying a Work Definition Code, the tool provides information such as the ordered sequence of operations and the materials and labor required at each step. This supports standardized maintenance processes and efficient creation of work orders based on predefined templates.

Maintenance teams can generate and update work orders using an AI agent to accelerate execution, ensure repair completeness, and ensure accuracy and prompt work order follow-up actions.

Steps to Enable

You can use AI Agent Studio to use or copy a preconfigured agent template to create Agents for your business processes. To automatically add a suffix to all artifacts in your agent team, you can Copy Template instead of Use Template. When you copy a template, you're directly taken to the agent team canvas where you can edit the agent team settings, agents, tools, and topics. The Use Template option takes you through a step-by-step process for configuring each artifact in the agent team.

For information on using AI Agent Studio, see How do I use AI Agent Studio?

Key Resources

Access Requirements

To access the Oracle AI Agent Studio for Fusion Applications and manage SCM AI agents, users must be assigned a configured job role that contains these duty roles:

  • SSCM Intelligent Agent Management Duty (ORA_RCS_SCM_AI_AGENT_MANAGEMENT_DUTY and ORA_RCS_SCM_AI_AGENT_MANAGEMENT_DUTY_HCM – both duty role codes are required)
  • Fai Genai Agent SCM Administrator Duty (ORA_DR_FAI_GENERATIVE_AI_AGENT_SCM_ADMINISTRATOR_DUTY)

In the Security Console, filter by Roles and Privileges to find the SCM Intelligent Agent Management Duty role. Filter by Roles and Permission Groups to find the Fai Genai Agent SCM Administrator Duty role.

To interact with AI agents in product pages, users must be assigned a configured job role that contains this duty role:

  • Fai Genai Agent Runtime Duty (ORA_DR_FAI_GENERATIVE_AI_AGENT_RUNTIME_DUTY)

In the Security Console, filter by Roles and Permission Groups to find this duty role.

To allow users to interact with agents, you must also enable permission groups in the Security Console on those users’ configured job roles that contain the Fai Genai Agent Runtime Duty role. You can enable permission groups when you manage the basic information of your configured job roles.

Users’ configured job roles must also contain privileges that allow access to the pages where AI agents are enabled.