All Products
Search

This Product

    Data Management:Data Agent for Analytics

    Document Center

    Data Management:Data Agent for Analytics

    Last Updated:Aug 20, 2026

    Data Agent for Analytics is an AI agent from the Alibaba Cloud ApsaraDB team. Describe your analysis goals in plain language — the agent interprets your data, proposes new avenues for analysis, and delivers results.

    Use cases

    • Business users: Define data requirements in plain language and generate reports on sales trends, user behavior, and more.

    • Data analysts: Run exploratory analysis, offload tasks like automated feature engineering and data cleaning to the agent, and reuse generated Python code.

    • Managers: Gain quick insights into key business indicators for data-driven decisions.

    Features

    • Automated insight discovery: Describe requirements in natural language. The agent interprets your data, discovers insights, and generates a report.

    • Faster time to value: Focus on business outcomes, not complex data workflows.

    • Seamless data connection: Natively supports ApsaraDB and DMS-managed data sources for instant analysis.

    Integrations

    • Core component: Data Agent Skill

    • One-click integration: Install from a Git repository or run the following command to quickly deploy and load the agent.

      npx skills add https://github.com/aliyun/data-agent-skill

    • Feature summary: Download and integrate this skill package into your agent service. It builds a secure bridge to your enterprise data sources through standard connection protocols, enhancing data access and analytical depth for custom data intelligence applications.

    Limitations

    Data Agent for Analytics is available in the following regions:

    China: China (Beijing), China (Zhangjiakou), China (Ulanqab), China (Hangzhou), China (Shanghai), China (Shenzhen), China (Chengdu), and China (Hong Kong).

    Asia Pacific: Singapore, Malaysia (Kuala Lumpur), Indonesia (Jakarta), Philippines (Manila), and Japan (Tokyo).

    Others: US (Silicon Valley) and US (Virginia).

    The DMS Data+AI module does not support viewing or aggregating token consumption. To check token usage:

    • Model Studio: Log on to the Model Studio console and choose Usage Statistics to view the number of model calls and the total number of tokens.

    • Billing Management: Log on to the Billing Management console and choose Bills > Bill Details to view the details of API call charges.

    The authentication systems of DMS Data Agent (RAM AccessKey pairs for OpenAPI and access tokens for the agent data gateway) are not interoperable with the OpenAI-compatible API keys of DashScope/Model Studio. You cannot use DMS credentials in tools such as QwenPaw that require OpenAI-compatible API keys. To call models in QwenPaw, use a DashScope/Model Studio API key.

    Interface layout

    • Initial interface:

      • Data Center: Add and upload data for analysis.

      • All Tasks: View the history of your analysis tasks.

      • User information: View details of the current account.

      • Chat area: Start a new analysis task and interact with the agent.

    • Workspace interface:

      • Chat area: Continue your conversation with the agent during the analysis.

      • Execution area: View the agent-written code and its corresponding results for each step.

    Account preparation

    Step 1: Create an account

    Create an Alibaba Cloud account for Data Agent. Create RAM users based on your business requirements.

    Step 2: Grant permissions

    Grant the Data Agent permission to the account. The policy name is AliyunDMSDataAgentFullAccess.

    Note

    This policy covers only the Data Agent feature permissions. Data access permissions must be requested and approved separately during use.

    Authorization methods:

    • Method 1: Grant permissions to an individual account

      1. Sign in to the RAM Users page with an account that has RAM administrator permissions.

      2. Find the RAM user and click Grant Permission in the Actions column.

      3. In the panel that appears, search for and select AliyunDMSDataAgentFullAccess, and then click Confirm Authorization.

    • Method 2: Grant permissions through a user group

      1. Sign in to the RAM User Groups page with an account that has RAM administrator permissions.

      2. Select the target user group. On the user group details page, click the Permissions tab, and then click Grant Permission.

      3. Search for and select AliyunDMSDataAgentFullAccess, and then click Confirm Authorization.

      4. Add the users you want to authorize to this user group.

    • Method 3: Identity federation for login-free access

      Integrate Data Agent into your enterprise system so that users can access the service without signing in to Alibaba Cloud.

    Procedure

    1. Log on to the Agent console.

    2. Choose an edition. Compare options in Data Agent editions.

      • Free Edition:

        On the Free version card, click Start Free Trial.

      • Personal Edition:

        • On the Personal card, click Upgrade to Personal Edition.

        • Select a region, the number of seats, and a subscription duration.

          Note

          In the Subscription Duration section, select a monthly duration.

        • Click Buy Now and complete the purchase.

      • Enterprise Edition:

        • On the Enterprise card, click Upgrade to Enterprise Edition.

        • Select a region, the number of Large Language Model (LLM) resource packages, and a subscription duration.

          Note

          In the Subscription Duration section, select a duration from 1 to 11 months.

        • Click Buy Now and complete the purchase.

    3. Upload a data sample from a local file or use existing data.

      • Click image to upload a local file. Supported formats: CSV, XLSX, and XLS (up to 200 MB).

      • Click image to use existing data. Add data in the Data Center.

    4. Describe your analysis requirements in the chat area and press Enter or click image to start the analysis.

    5. Review the execution plan generated by the agent.

      • If the plan is satisfactory, click Start Task.

      • If not, click Modify Tasks to provide additional details until the plan meets your needs.

    6. Wait for execution. You can view the agent's code and results for each step.

    7. The agent can generate a visual web report to present data insights.

    Data Center

    In the left-side navigation pane, click Data Center. Click Add data and select a connection method.

    • Local upload:

      Drag a file to the upload area or click to select one. After upload, click Confirm.

    • Cloud databases: The Free and Personal Editions support RDS Database, PolarDB database, and AnalyticDB Database. The Enterprise Edition supports 40+ data sources listed in Databases Supported by DMS.

      1. Select a region and an instance.

      2. Enter the Database user name and Database password.

      3. Click Test link to continue.

      4. Select the database and table.

      5. Click Confirm.

    • DMS-managed instance:

      You can connect MaxCompute and Hologres instances that are registered in DMS as data sources for analysis. For the registration procedure, see Register an instance.

    FAQ for adding data

    Tables do not appear after you add a MaxCompute instance

    MaxCompute instances purchased after 2024 require the tenant-level Information_schema and must be upgraded to the Schema hierarchy. Follow these steps:

    1. In the MaxCompute console, go to Project Management and click Upgrade to Schema Hierarchy.

    2. Grant the tenant-level admin permission to the user identity that corresponds to the AccessKey pair used when registering the instance in DMS.

    3. In DMS Instance Management, click Edit next to the target instance, and then click Save to trigger Schema hierarchy detection.

    Connection error when you add a Hologres instance

    DMS requires a specific VPC endpoint to connect to Hologres instances.

    For VPC endpoint configuration, see Hologres instance configurations.

    Tables or databases do not appear in the dropdown list

    Click the refresh button. For a small number of tables, a re-search within 30 seconds should return results.

    Permission denied when refreshing tables

    The user must have RAM permissions for the database resource or hold the DMS administrator or DBA role.

    • Option 1: RAM policy authorization

      Grant the user a RAM policy for the corresponding cloud service. Common system policies:

      Engine

      Action

      Resource ARN

      System policy

      RDS

      dms:LoginDatabase

      acs:rds:{region}:{accountId}:dbinstance/{instanceId}

      AliyunRDSFullAccess

      PolarDB

      dms:LoginDatabase

      acs:polardb:{region}:{accountId}:*/{instanceId}

      AliyunPolardbFullAccess

      AnalyticDB MySQL

      adb:*

      acs:adb:{region}:{accountId}:dbcluster/{instanceId}

      AliyunADBFullAccess

      AnalyticDB PostgreSQL

      gpdb:*

      acs:gpdb:{region}:{accountId}:dbinstance/{instanceId}

      AliyunGPDBFullAccess

    • Option 2: Grant the user a DMS administrator or DBA role

      Grant the user an administrator or DBA role in DMS. For more information, see Manage users.

    Long-term memory

    The agent automatically identifies and saves key information from your conversations as long-term memory. This memory is recalled in future sessions to better understand your business requirements, improve analysis results, and provide a more contextual experience.

    Manage memory settings

    This feature is enabled by default. To stop automatic memory storage, disable it.

    Memory list

    On the Memory page, you can view and manage all stored memories:

    Field

    Description

    Source

    The conversation where the memory was generated. Click the link to view the original conversation.

    Content

    The key information the agent extracted from the conversation.

    Heat

    A score based on recall frequency. A higher heat value indicates the memory is more actively used in your analyses.

    Status

    Memories have two statuses:
    • Remembered: The memory is active and can be recalled in subsequent analyses.
    • Forgotten: The memory is inactive and will not be recalled.


    Operation

    Edit or delete memories in the Actions column:

    • Edit: Click the edit icon to correct or update a memory. In the dialog box that appears, you can manually correct or complete the memory content and then save it. This ensures that the agent learns the most accurate information.

    • Delete: Click the delete icon to remove a memory. The effect depends on the memory's status:

      • For a Remembered memory: The status changes to Forgotten. The record remains in the list and can be reactivated.

      • For a Forgotten memory: The memory is permanently removed and cannot be recovered.

    Data privacy

    • The agent does not use your data — including uploaded files, queries, analysis results, and reports — for model training or iteration.

    • Your data is processed in an exclusive computing instance within your account. The instance and its data are destroyed after the task completes. Other accounts cannot access your data, processes, or history.

    • For local file analysis, uploaded files are stored in an isolated environment not visible to other accounts.

    • For database analysis, data stays in your database instance. No data is migrated during computation. All intermediate results are destroyed after analysis.