Data-Based Agent

After completing the configuration of Data Sources, Data Catalog, and Business Domains in the Data Asset module, these data can be applied to the Agent to achieve data-driven intelligent Q&A or business automation capabilities.

Such Agents are called Data-Based Agents (Data Agents). They can directly access tables and views in the business domain to provide more accurate and evidence-based answers or operations.

Configuring Data Sources in Basic Agent

1. Go to the Basic Agent Configuration Page;

2. Find the "Data Source" area and click the "+" button on the right;

3. Select the data source you want to add from the pop-up list (which corresponds to the previously configured business domain);

4. Click Confirm and save the Agent configuration;

5. Publish the Agent.

After completion, the Agent can call tables or views from the data source in real-time during Q&A, enabling queries and answers based on actual business data.

Configuring Data Source Nodes in Advanced Orchestration Agent

1. Open the Advanced Orchestration Assistant page;

2. Click "Add Node" and select Data Sources as the node type;

3. Choose the corresponding data source (i.e., business domain) from the list;

4. Place the node at the appropriate position in the workflow and connect it with other logic nodes (such as conditional judgment, API calls, knowledge Q&A, etc.);

5. Save and publish the workflow.

After publishing, the Agent will automatically call the configured data source nodes according to the orchestration logic during execution, thereby introducing real-time data into Q&A or business decision-making.

Notes and Best Practices

• Keep Business Domain and Data Synchronization Consistent
  If the table structure or fields in the business domain are updated, resynchronize in the Data Asset module; otherwise, the Agent may encounter missing fields or query errors during calls.

• Data Source Permission Control
  Ensure that the data sources bound to the Agent have access authorization to avoid insufficient query permissions or connection failures.

• Use Data Nodes Reasonably
  In advanced orchestration, place data nodes reasonably according to business logic to avoid repeatedly calling the same data multiple times in a single session, improving response speed and performance.

Q&A Effect of Data-Based Agent

After configuring the data source, enter the Agent dialogue interface to test the ticket analysis assistant. Below is an example interaction flow:

1. Enter a natural language request in the dialogue box

   Tell me the Bank Loan Information.
   

As shown in the figure:

2. The agent will first extract relevant data from the connected data sources. Through the comprehension and analysis of a large language model (LLM), it will generate a structured, summarized response. This response will outline key findings, trends, and main points, directly addressing the user’s query in natural language and may include suggested next steps.

3.Below the response, the system also provides an Intelligent BI Analysis Zone that supports the following functional operations:

• Data Preview: View the raw data used to generate the chart;

• Chart Editing: Switch the bar chart to line chart, pie chart, etc., and customize X-axis and Y-axis fields;

• SQL Query View: View and copy the SQL query behind the current analysis for further analysis or reuse;

• View Data: Click to jump to the original data table view;

• Intelligent Insights: Click to have the system provide automated insights based on the current data, such as trend analysis, anomaly detection, etc.

Data Preview:

Chart Editing:

SQL View:

The overall Q&A effect is as follows:

By configuring business domains into the Agent, AI Central achieves a complete linkage from data assets to intelligent agents, enabling the Agent to no longer rely solely on knowledge Q&A but to perform intelligent queries, analysis, and decision-making based on real enterprise data.