After purchasing and activating Intelligent Analysis Agent, Intelligent Analysis Agent currently provides you with a general agent (default name: DataAgent). You can directly use the pre-configured general agent to consult on issues, and you can also create and configure custom agents. This article will guide you through quickly using both the general agent and custom agents, and completing analysis tasks with the general agent.
To learn about the comparison between the two, refer to Agent Type Description: General & Custom Agents.

The following conditions are required to use the general agent:

• Account and permissions: You need to have a valid platform account and be successfully logged in to the system; please ensure your account has been granted permission to use the general agent. If not yet enabled, contact your system administrator.
• Understand the data: Connect relevant data or upload files, and briefly describe the background or source of the core business data connected to the Intelligent Analysis Agent.

1. After purchasing the Intelligent Analysis Agent service, log in to the DataAgent interface using your account and password.
2. After entering the product page, select the corresponding region, click the New Project button at the top right of the page, fill in the project name, select the project administrator, and fill in the reason for creation field. When finished, click the Confirm button.

3. After creating the project, set project information, add users, and grant permissions in the project center.

1. After authorization is complete, click the Agent button at the top of the page to enter the agent usage interface.
2. In the left navigation bar of the Intelligent Analysis Agent usage interface, you can see all agents you have permission to access and use in the current region. Click the agent name to enter the agent.
   • The DataAgent at the top of the list is the general agent.
   • The other agents below in the list are the custom agents you have created. For details on creating a custom agent, see Overview of the Creation and Configuration Process.

3. In the central dialog in the agent interface, use the Q&A service and click the Connect data button in the lower right corner to upload a data source. After the data source is uploaded, enter the task description in the dialog. In addition, the following features are available:
   • Select whether to enable internet access: When internet access is enabled, the agent retrieves the latest information from the internet in real time and analyzes it based on the latest information. To disable internet access, click the internet access button again. If the button is grayed out, internet access is disabled.
   • Configure extended capabilities: The general agent allows you to select and configure different extended capabilities as needed (multiple selections supported). The following is an explanation of extended capability configuration.

4. After uploading the data source and providing the task description for the general agent, click the send button and wait for the agent to execute the task.
5. The task execution time will vary depending on the complexity of the task. Please wait patiently. After the task is completed, the general agent will return the execution result, which you can view in the dialog. Analysis results are available in two types: Web version and Document format. You can click the corresponding button type to view different types of analysis results.
   There are several operations you can perform on the analysis results. The following are illustrations and descriptions of the related operation items.

Prepare data #

Before performing intelligent data analysis, you need to import the data to be analyzed into the intelligent analysis agent. Currently, uploading data files and connecting to a data warehouse are supported. For details, see Data Preparation Overview. A sample data is provided below. You can download the sample data and upload it to quickly experience the data preparation process.

1. Select Data Preparation—Data Connection, and click the New button to create a data connection.

2. Select the Excel data connection method and click to upload the provided sample dataset for the analysis Agent.

Intelligent Analysis Agent Dataset Sample.xlsx

Unknown size

3. Select the sample data. After seeing the upload success prompt, click the Next Step button.

4. After previewing the data and confirming it is correct, click the Confirm button. Once the data connection is created successfully, you can view the basic information and lineage view of the uploaded Excel data in the data connection list.

5. Select Data Preparation—Dataset and click the New Dataset button.

6. In Add Data Connection, select Upload to Sample Dataset.

7. Drag the selected data table into the dataset creation area and click Save.

8. Set the dataset information, configure relevant parameters, and click the Confirm button.

9. The dataset is created successfully. You can perform dataset operations such as data preview, field modification, and setting row and column permissions.

10. After the dataset is created successfully, click the Enable DataAgent Analysis Capability button, then click the Enable button. Choose the data update mode and whether to synchronize in real time based on the actual data update situation. Click the Confirm button and wait for data vectorization. When the vectorization status shows "Success", only then can the created dataset be configured in the agent. The expected wait time is 15+ minutes.

Create an agent #

You can create multiple intelligent analysis agents within the Intelligent Analysis Agent based on your business data analysis requirements.

1. Create an agent. Go to the configuration page of the Intelligent Analysis Agent and click the Create Agent button in the upper right corner.

2. Configure the basic information for the agent, including application name, application description, avatar, administrator, and members.

3. Configure the agent.

1. Go to the agent's dataset configuration module and click the Add Dataset button located in the center.
2. Search for the datasets you need to add. This page supports batch selection of multiple datasets.
3. After clicking the Confirm button, the dataset will be added successfully. You can continue to add other datasets or remove datasets as needed.

4. Publish the agent. After configuring the agent, you need to click the Publish button in the upper right corner for the agent to appear in the list of published agents and be available for use.
   Once published, users with agent permissions can click the agent in the published agents list to enter its page, and can find authorized agents in the agent list on the left side.

Use the agent #

1. After authorization by the primary account, the sub-account can log in to the agent using the account password and click "Agent" to enter the agent list page.
2. Click a published agent to enter the conversation page and use the intelligent analysis agent.

3. After entering the agent conversation interface, click the switch button in the dialog box to toggle between intelligent Q&A and in-depth research features.

4. Users can click the dialog box to select built-in questions to ask , or directly enter questions to ask.

   Natural language queries	Quickly view recommended questions
   The main usage of the intelligent agent is that users can directly describe their data query requirements to the agent using text. After the agent replies, users can click "Follow-up" to continue interacting with the agent regarding related questions. When querying data with the intelligent agent, there is no need to select a dataset; it will automatically query data from the configured datasets	Recommended questions are provided below the dialog box, and users can click any recommended question to directly query data. Recommended questions are automatically generated based on everyone's historical queries, and can also be customized. For specific configuration methods, see Overview of the Creation and Configuration Process.

   • For more instructions on using the analysis agent, see Intelligent Data Query Agent, Deep Research Agent, Web Search, Knowledge Document Configuration.
   • To integrate the published intelligent analysis agent into office software for use, or to use the intelligent analysis agent directly by calling OpenAPI, see Intelligent Analysis Agent Third-Party Integration Guide, Invocation Method.

1. All content output by this service is generated by artificial intelligence models.
2. This feature is intended only for customers' internal, proprietary business, and personal use. Customers must not provide generative artificial intelligence services to the public through DataAgents.
3. This product supports both SaaS and private deployment versions. To purchase or request a trial, please contact the sales staff for consultation.