Agent Use

  • Edit Times:6
  • Recent Updates:Charis.Dong on 2026-06-17
  • Description

    Function Description

    The Data Agent workbench provides an agent-based intelligent chat entry. Users can directly select a pre-configured agent to quickly complete tasks, such as data queries, knowledge retrieval, and analysis report generation, through natural language chats.

    Application Scenario

    • Daily data queries: Business personnel can directly ask agents questions to quickly obtain business data such as sales amounts, inventory, and orders.

    • Analysis by multiple rounds of chats: Users can ask follow-up questions within the same chat to gradually delve deeper into business issues.

    • Chat history review: Users can quickly find and resume previous analysis chats via the left history panel.

    Effect Demonstration

    Taking the chain operation analysis scenario as an example, select the Chain Operation Analysis agent, and enter the question "Sales amount per state in 2025". The agent will automatically parse the question, fetch data from the data source, and return the results. The following figure shows the effect.

    Follow-up questions, for example, "Top 3 states in the Southwestern United States", can be asked to further refine the analysis dimensions. The following figure shows the effect.


    Procedure

    Agent Selection

    Log in to Data Agent. All published agents are displayed as cards on the workbench. You can quickly locate a target agent using the search box at the top. Click the target agent's card to enter its chat page, as shown in the following figure.

    Chat Creation

    To start a new analysis task, click the left New Chat button to clear the current chat context and begin a fresh chat. Chat history is displayed on the left panel. You can click one to enter a historical chat and continue unfinished analysis.

    iconNote:

    Each time you click New Chat, an independent chat context will be started. The agent does not remember the content of the previous chat. Ask follow-up questions within the same chat.

    Talking to the Agent

    Asking the Agent Questions

    In the input box in the middle of the page, enter your question (for example, "What can you help me with?"), and click the sending button (or press Enter) to submit the question.

    Analysis and Result Returned by Agent

    The agent will automatically parse the intent of the question, invoke the corresponding skill, and return the result within the chat area.

    Further Asking

    For further analysis, you can ask follow-up questions within the same chat, for example, "Top 3 cities in California".

    Chat Correction

    Chat correction is primarily applicable to the following two types of business scenarios:

    • Agent response deviation scenario: If the agent's output contains errors or fails to meet user expectations, users can directly raise objections, correction requests, or adjust instruction strategies. The agent will automatically review and reflect on its output, and regenerate a compliant result.

    • User query error scenario: When a user-entered question is deviated and the agent has already entered the response generation process, users can directly resend a concise and correct question in the chat box. The agent will automatically interrupt the original task and respond based on the latest correct question.

    Chat Operation

    Chat Feedback

    After the agent outputs content, you can click the thumbs-up or thumbs-down icon below to provide real-time feedback on the chat quality.

    Regeneration

    If the data, knowledge, and skills associated with the agent are adjusted, or no content is output due to network issues, click  (Regenerate).

    Chat Sharing

    You can select multiple chat content items and share them via a link for other users within the platform to view.

    iconNote:
    Chats are shared with only the final result via snapshot, not containing any agent's thinking and analysis process.

    使用Agent 图1.gif

    Report Operation

    Report generation agents additionally provide the following convenient operations to meet viewing and distribution requirements in different scenarios:

    • Sharing by link: A link dedicated to viewing is generated to easily share the report with users within the platform, allowing multiple users to collaboratively view the report in real time.

    • Export: The report can be downloaded as a Word or PDF file to meet the requirement of sharing with users outside the platform.

    • Full-screen display: You can switch to the full-screen mode to optimize the visual interaction experience and enhance immersion in report reading.

     使用Agent 图2.gif

    Attachment List


    Theme: Quick Start
    • Helpful
    • Not helpful
    • Only read