All Products
Search

This Product

    Platform For AI:Deploy a dedicated QwenPaw agent using PAI-EAS in 5 minutes

    Document Center

    Platform For AI:Deploy a dedicated QwenPaw agent using PAI-EAS in 5 minutes

    Last Updated:Aug 25, 2026

    Deploy the QwenPaw personal agent framework on Platform of Artificial Intelligence–Elastic Algorithm Service (PAI-EAS) and use it with custom PAI-EAS models or Alibaba Cloud Model Studio models to quickly build a dedicated AI assistant. QwenPaw is a local-first, self-hostable framework open-sourced by the AgentScope team in February 2026. It lets you control inference costs through a Coding Plan.

    Deploy an EAS service

    1. Log on to the PAI console. Select a region on the top of the page. Then, select the desired workspace and click Elastic Algorithm Service (EAS).

    2. On the Inference Service tab, click Deploy Service, and then in the Scenario-based Model Deployment area, click QwenPaw Deployment.

    3. Configure the key parameters:

      Parameter

      Description

      Service Name

      Example: qwenpaw_demo.

      Image Configuration

      Select the Latest version.

      Resource Configuration

      Select a CPU instance type and configure it as needed. The default is ecs.c7a.large.

      Model Settings

      Select an OSS path for persistent storage of QwenPaw configurations, such as oss://examplebucket/qwenpaw/.

      VPC

      Create and configure a virtual private cloud (VPC), vSwitch, and security group.

      Note

      QwenPaw requires public network access to search or use a browser. Select a VPC that is already configured for public network access.

    4. Click Deploy. The deployment is successful when the service status changes to Running.

    Configure public network access

    An EAS service accesses the public network through an Internet NAT gateway. The configuration steps are as follows. For more information, see Internet NAT Gateway.

    1. Create an Internet NAT gateway and attach an EIP

    Go to the NAT Gateway – Internet NAT Gateway purchase page.

    • Billing Method: Pay-as-you-go.

    • Region: Select the region where the EAS service is located.

    • Network and Zone: Select the VPC configured for the EAS service. This setting cannot be changed after creation.

    • EIP: Select an unattached elastic IP address (EIP) or purchase a new one.

    2. Configure an SNAT entry

    Go to the Internet NAT Gateway page. Find the Internet NAT gateway that you created, and in the Actions column, click Configure SNAT . Click Create SNAT Entry.

    • SNAT Entry: Select VPC Granularity.

    • Select EIP: Select the configured EIP.

    Start the WebUI

    1. In the Invoke/Log/Monitoring column, click the image button to go to the WebUI page.

      On the Inference Service tab of Elastic Algorithm Service (EAS), find your service. The Invoke/Log/Monitoring column contains three icons. Click the first icon to open the WebUI.

    2. Configure the model. Go to Settings > Model to configure the Provider. In the LLM Configuration area, select a provider and a model.

      Aliyun Coding Plan

      Go to the Coding Plan page to subscribe to the service and obtain your dedicated API key.

      On the model settings page, find the Aliyun Coding Plan provider card and click the Settings button in the lower-right corner. In the dialog box that appears, the base URL is pre-filled with https://coding.dashscope.aliyuncs.com/v1. Paste your API key into the API Key field and click Save to complete the configuration.

      Add an EAS model service

      1. Click to add a provider. Set Protocol to OpenAI Compatible.

      2. Set the URL and API key. For more information, see Obtain an endpoint and token. Append /v1 to the endpoint. In the Base URL field, enter the endpoint of the PAI-EAS service. In the API Key field, enter the corresponding API key. Click Test Connection to validate the configuration, and then click Save.

      3. Add a model. On the PAI-EAS provider card, click Model to open the model management dialog box. Then, click + Add Model.

      DashScope

      On the DashScope provider card, click Settings to add an Alibaba Cloud Model Studio API key. For more information, see Select a model to add more models.

      In the Configure DashScope dialog box that appears, the Base URL is pre-filled with the default value. Paste your key into the API Key field, click Test Connection to verify connectivity, and then click Save.

    3. Start a conversation with or assign a task to the QwenPaw personal assistant.

      For example, select the Qwen3.5 Plus model and enter "Tomorrow's weather in Hangzhou" in the chat input box. QwenPaw uses multi-step reasoning and the browser_use tool to automatically retrieve web information and return the weather forecast, such as weather conditions, temperature range, and wind level.

    Channel configuration

    QwenPaw supports integration with channels such as DingTalk and Lark. For more information, see Channel Configuration.