Overview
This article explains how to configure an AURA AI Agent using a Proactive AI Workflow and a Business Workflow. Once the configuration is complete, the agent can be used in Talk to Your Data to retrieve and analyze data from the configured sources.
Prerequisites
Before configuring an AURA AI Agent, ensure that the required data connections are available and that you have the necessary permissions to create AI Orchestration workflows and AI Agents.
Step 1: Create a Business Workflow
Business Workflow is responsible for defining the data sources that the AURA AI Agent will use to fetch information.
From the left navigation panel, navigate to Administration > AI Orchestration > Workflows.
Click Add Workflow.
Select Business Workflow as the workflow type and create the workflow.
After the workflow is created:
Open the Designer tab.
Configure the data connections from which the workflow should retrieve data.
Define the required source configuration using YAML.
For instructions on configuring the Business Workflow, refer to the "AI Orchestration Workflows – Step Reference Guide" article.
Once the data connections have been configured successfully, the Business Workflow is ready to be used by a Proactive AI Workflow.
Step 2: Create a Proactive AI Workflow
Next, create the workflow that will orchestrate the data retrieval process.
Navigate to Administration > AI Orchestration > Workflows.
Click Add Workflow.
Select Proactive AI Workflow as the workflow type.
From the Add Relationship section, add the required Hydration Queries to the Proactive AI Workflow.
Configure a Scan Query that will be used to retrieve the relevant data during workflow execution.
Save the workflow.
After the workflow is created:
Open the workflow details page.
Create a new relationship.
Select Uses On-Demand Hydrator as the relationship type.
Choose the Business Workflow created in the previous step.
This relationship enables the Proactive AI Workflow to retrieve data using the configured Business Workflow whenever it is executed.
Important: Ensure that the name of the Hydration Query exactly matches the name referenced in the Business Workflow. If the names do not match, the workflow will not be able to hydrate the data, and the required data retrieval will fail.
Step 3: Configure AI Skills (Optional)
AI Skills allow you to define operator-specific instructions that guide how the AURA AI Agent analyzes data and diagnoses problems. The system includes predefined AI Skills that provide built-in diagnostic behavior. However, you can augment these capabilities by adding your own instructions tailored to your organization's operational requirements or domain-specific troubleshooting practices.
Custom AI Skills are associated with Data Domains. When a Data Domain is attached to a Proactive Workflow, the AI Skills defined for that domain become available to the AURA AI Agent during execution, allowing it to incorporate domain-specific knowledge and troubleshooting guidance alongside its predefined capabilities.
To configure AI Skills:
Open the configured Proactive Workflow.
Add the required Data Domain to the workflow.
Save the Proactive Workflow to apply the updated AI Skills and make them available for use.
These instructions are considered during AI Agent execution, enabling more tailored and context-aware responses while preserving the system's built-in capabilities.
Step 4: Configure an AURA AI Agent
Once the Proactive AI Workflow has been configured, it can be associated with an AURA AI Agent.
- Navigate to Data Sources → {REST API Source Name} → AI Agents.
- Click Add Agent.
- Select Aura AI Agent.
- Under Workflow Assignment:
- Select the required Solution Type (for example, HFC Fiber Node or HFC Driver).
- Select the required Proactive Workflow.
- Select the Reasoning Effort:
- Fast – Prioritizes faster responses.
- Balanced – Balances response speed and analysis quality.
- Deep – Performs more comprehensive analysis.
- Click Save.
The AI Agent is now configured to execute the selected Proactive AI Workflow.
Notes
- The available Solution Types are configured under Administration → Account → Module Settings → AI Orchestration.
- The selected workflow is associated with the Aura AI Agent and can be viewed from the workflow details.
- Each Aura AI Agent can be associated with only one Proactive Workflow.
Once the agent is saved, the selected Proactive Workflow is automatically associated with the agent. You can verify this association from the corresponding Workflow details.
Step 5: Use the AURA AI Agent in Talk to Your Data
After the AI Agent has been configured:
Navigate to Talk to Your Data.
Select the configured AURA AI Agent.
Start interacting with your data using natural language queries.
When a request is submitted, the AURA AI Agent invokes the configured Proactive AI Workflow, which in turn uses the associated Business Workflow to fetch data from the configured sources. The retrieved data is then processed and returned to the user for analysis.
Node Incident
- Go to Asset Dictionary.
- In Asset Type, select Fiber Node Incident.
- Choose any node from the list.
- Open the Details page for that node.
- Click Engage.
Nodes can be analyzed directly from the node incident details page. Navigate to the required node incident, ask questions related to the selected node. The system analyzes the node-level data and provides relevant insights and results.
Once the analysis is performed on the Incident Details page, the corresponding analysis chat becomes available in Talk to Your Data. When a user selects that incident chat from the Talk to Your Data screen, they are redirected to the conversation associated with the same Fiber Node Incident.
Workflow Overview
The overall execution flow is as follows:
Business Workflow → Proactive AI Workflow → AURA AI Agent → Talk to Your Data
The Business Workflow defines how data is retrieved from external sources.
The Proactive AI Workflow orchestrates the execution and uses the Business Workflow through the Uses On-Demand Hydrator relationship.
The AURA AI Agent executes the configured Proactive AI Workflow.
Talk to Your Data serves as the user interface where the configured AURA AI Agent can be used to analyze the retrieved data.
For the complete process of configuring Network Intelligence AI and AURA Agents, refer to the "Network Intelligence AI" article.
0 Comments