The AI Assistant service is an AI-powered assistant built by DataWorks on the OpenClaw framework. It supports direct conversations through the DataWorks console (web client) and integrates with IM platforms such as DingTalk and Feishu, enabling you to perform alert analysis, task diagnosis, code modification, O&M, and data governance through natural language. DataWorks provides one-click network setup between resource groups and IM clients, knowledge base management, Skill management, scheduled task management, and audit logging to help you quickly build a dedicated enterprise-grade AI assistant.
Features
The AI Assistant service is a dedicated intelligent assistant launched after DataWorks integrated OpenClaw. Unlike the built-in agent in the DataWorks console, the AI Assistant service extends platform capabilities to the Web client and IM clients (DingTalk, Feishu, and WeCom), enabling you to complete tasks without opening the DataWorks console.
Core values
Multi-client access: Access the AI assistant from the Web client (DataWorks console) or IM clients (DingTalk, Feishu, and WeCom group chats) anytime, anywhere.
Instant response: Receive alerts and run AI-powered diagnoses directly in your IM group, reducing response times from minutes to seconds.
Intelligent diagnosis: Automatically analyzes root causes of task failures and the impact scope of alerts, and suggests fixes.
Interactive O&M: Use natural language to issue O&M commands, such as rerunning tasks or modifying resource groups. All write operations require confirmation before execution.
Knowledge enhancement: Build a knowledge base automatically through retrieval-augmented generation (RAG) and memory management, improving the AI assistant's understanding of your business context.
Scheduled inspections: Built-in templates for scheduled and triggered tasks cover SLA monitoring, asset governance, cost analysis, and more, delivering inspection reports on a regular basis.
Data security: All data remains within the DataWorks platform. AI inference runs on the platform's internal network, and sensitive data is desensitized before being sent to the AI.
Available regions and policies
Join the AI Assistant service DingTalk group for more technical support.
Available to customers using DataWorks Basic Edition or higher.
Available regions: China (Zhangjiakou), China (Beijing), China (Ulanqab), China (Hangzhou), China (Shanghai), China (Shenzhen), China (Chengdu), China (Hong Kong), Singapore, Malaysia (Kuala Lumpur), Indonesia (Jakarta), Japan (Tokyo), and US (Virginia).
Core capabilities
The AI Assistant service uses a data O&M agent to cover the following core scenarios:
Scenario | Core capabilities | Example commands |
Fault diagnosis (core strength) | Alert diagnosis (root cause identification and upstream analysis), instance diagnosis (single or batch), and workspace health diagnosis |
|
Task scheduling | Task configuration query/modification, instance query/rerun/termination/mark as succeeded, task freeze/unfreeze, priority adjustment, dependency topology viewing, and resource group migration |
|
Workflow management | Workflow query/modification, backfill/smoke test, manual trigger/start/stop/rerun, and dependency refresh |
|
Monitoring and O&M | Baseline configuration/SLA query, alert rule management, alert message query, and on-call schedule query |
|
Data quality | Data quality monitoring rule management, quality alert rule management, and automatic quality monitoring configuration |
|
Data governance | Tag management (create/bindunbind), governance issue/rule queries, asset analysis (storage/compute/synchronization/scheduling), asset health scores, governance inspections |
|
Project management | Workspace list/details queries, member list/role list queries, current user information queries |
|
Resource management | Resource group list/details queries, resource group utilization monitoring |
|
The AI Assistant service currently supports the following capabilities in read-only mode: member permission management and role management in project management, and network configuration in resource management. The AI Assistant service does not support creating workspaces, creating new tasks/nodes, or deleting workspaces/tasks.
Supported IM platforms
IM platform | Required configuration | Configuration reference |
DingTalk | Client ID, Client Secret | |
Feishu/Lark | App ID, App Secret | |
WeCom | Bot ID, Secret |
Prerequisites
Make sure that you have activated the DataWorks Data Agent feature. If you have not activated it, see Activate DataWorks.
Prepare a serverless resource group to run the AI Assistant service instance. An AI Assistant service instance requires at least 2 CUs of resources.
To use the service through an IM client, you must have created a bot application on DingTalk or Feishu and obtained the required configuration information, such as AppKey/AppSecret (DingTalk) or App ID/App Secret (Feishu).
Create an instance
Log on to the DataWorks console, select the desired region, and in the left-side navigation pane, click AI Assistant Service.
On the AI Assistant Service page, click Create.
In the Create AI Assistant Service Instance dialog box, configure the following settings:
Parameter
Description
Instance Name
Required. The name of the AI Assistant service instance, used to identify and distinguish different instances. The name must start with a letter or Chinese character and can contain letters, Chinese characters, digits, underscores (_), and hyphens (-). The name cannot exceed 128 characters in length.
Resource Group
Required. Select a serverless resource group to run the AI Assistant service instance. An AI Assistant service instance requires at least 2 CUs of resources.
NoteIf the available CUs of the selected resource group are insufficient to meet the resource requirements of the AI assistant service instance, the resource group is unavailable for selection.
Execution Identity
Required. Specify the identity that the AI Assistant service uses to access DataWorks. If you use the AI assistant only as a personal assistant, we recommend that you set this parameter to Current Logon User. If you want to share the AI assistant with multiple users, we recommend that you set this parameter to Create New RAM Role, which allows you to specify the workspaces and workspace roles that the role can access.
Instance description
Optional. The description of the instance. The description can be up to 256 characters in length.
Click OK.
Creating an instance takes approximately 1 to 3 minutes. After the instance is created, you can start using the AI assistant.
Manage instances
Basic operations
On the AI Assistant service page, you can view and manage the AI assistant service instances that you have created.
Start/Stop an instance: An instance is started by default after it is created. After you modify the instance configuration, you can stop and then restart the instance for the configuration to take effect.
Upgrade an instance: When the image version of the instance is earlier than the latest version, you can click the Upgradable tag next to the image column in the instance list to upgrade the instance to the latest version and obtain new feature support.
Execution Role Management: Modify the access permissions of a specified identity. You can edit the list of accessible workspaces and workspace roles.
Edit instance: Modify the instance name and description.
Delete instance: Click Delete in the Actions column of the target instance to delete the instance.
Retry: For instances that failed to be created or started, you can click Retry to re-execute the operation.
Only the instance owner, the Alibaba Cloud account, or users with the AliyunDataWorksFullAccess permission can edit or delete instances.
Channel configuration
The AI Assistant service supports configuring IM client channels, enabling you to communicate with the AI assistant directly through DingTalk, Feishu/Lark, or WeCom without opening the DataWorks console. If you do not configure an IM client channel, you can still use the AI assistant through the Web client.
Click the configuration button for a channel type, and enter the required IM client information in the dialog box that appears:
DingTalk: Enter the Client ID and Client Secret.
Feishu/Lark: Enter the App ID and App Secret.
WeCom: Enter the Bot ID and Secret.
After the configuration is complete, you can click Test Network Connectivity to verify whether the network connection is established. If the network is not connected, click One-Click Network Setup to configure the network. Two solutions are currently supported:
PrivateZone + Private Link (recommended): If the resource group is deployed in a VPC that does not have public network access enabled, use this method to allow resources within the VPC to access IM platform endpoints through a purely private network, ensuring that traffic never leaves the private network.
This solution requires a vSwitch in the specified availability zone. If a vSwitch has not been created, create one as prompted on the page.
Enable public network access: Connects to the public network through a NAT gateway and EIP. The configuration is simple, but offers lower security.
If the AI Assistant service has scheduled inspection tasks or scheduled tasks configured and needs to precisely @mention the responsible person in the corresponding chat group, you need to configure account mapping. For more information, see AI assistant in practice: Configure IM account mapping.
Different network connectivity solutions incur different billing methods. For details, see Billing.
Skill management
A Skill is an extensible capability module that the AI assistant can invoke. Through Skill management, you can extend the capability boundary of the AI assistant in data O&M and governance scenarios. The AI Assistant service supports built-in system skills and user-defined custom skills: system skills are provided and maintained by the platform and cover scenarios such as data development assistance and product Q&A custom skills allow you to upload proprietary capability modules to meet personalized business requirements.
Click the name of the target instance to go to the instance details page. On the instance details page, click the Skill Management tab.
The Skill Management tab is visible only when the instance image version is v3.0.0 or later. If you do not see this tab, upgrade the instance image version first.
System skills
Built-in system skills are provided and maintained by the DataWorks platform. The following system skills are currently available:
Data Development Skill: Supports data development assistance capabilities such as code analysis and SQL generation.
Full-Series Product QA Skill: Supports Q&A about DataWorks product usage.
System skills cannot be deleted. You can enable or disable them by using the toggle control.
Custom skills
Import a Skill
On the Skill Management tab, click Import Skill.
In the Import Skill dialog box that appears, configure the following information:
Parameter
Type
Required
Description
Name
Text field
Yes
The name of the Skill, used for identification and differentiation. Maximum 64 characters.
Description
Text area
No
A description of the Skill to help understand its purpose. Maximum 256 characters.
Skill file
File upload
Yes
The compressed Skill file. Only .zip format is supported. Drag-and-drop upload is supported.
After the configuration is complete, click Confirm to complete the import.
Enable/Disable a Skill
In the Skill list, use the toggle on each Skill card to enable or disable a Skill in real time. After a Skill is disabled, the AI assistant no longer invokes the capabilities of that Skill.
Upgrade a Skill
When a new version is available for a system Skill, an Upgradable tag is displayed on the Skill card.
Click the Upgrade button.
The system automatically disables and re-enables the Skill. The upgraded Skill takes effect immediately.
Delete a custom Skill
In the Skill list, find the custom Skill that you want to delete, click the Delete button, and confirm the deletion.
System Skills cannot be deleted. Only custom Skills support the delete operation.
Get more Skills
On the Skill Management tab, click Alibaba Cloud Skill Portal to go to the Alibaba Cloud Skill Portal page and browse or obtain more available Skill modules.
Memory management
The long-term memory feature helps you persist critical business context for an AI assistant instance. Through memory management, you can save important knowledge such as project asset information, data standards, and business processes as files to the AI assistant instance. This allows the instance to maintain an understanding of this context across sessions, providing more accurate and personalized O&M recommendations.
On the AI Assistant service list page, click the name of the target instance to go to the instance details page, and then click the Memory Management tab.
Browse directory: Browse memory files in a tree directory structure. You can navigate into subdirectories and go back to the parent directory.
View file: Click a file to view its content. For large memory files, the content is truncated with a truncation notice displayed.
Import memory: Upload files to a specified path. You can export memory from a local OpenClaw instance or another AI assistant service and import it to enable memory reuse.
Export: Supports single-file download or batch export as a package.
Delete: Supports deleting individual files or batch deletion.
Knowledge base management
The knowledge base has been separated from the AI Assistant service into an independent module called Context Graph (Knowledge Base), which provides unified creation and management. Knowledge bases created in Context Graph (Knowledge Base) can be authorized to the AI Assistant service or Data Agent through Share. For information about the features, creation methods, and usage of knowledge bases, see Context Graph (Knowledge Base).
Newly created AI assistant services no longer generate a local knowledge base. To provide knowledge for an AI assistant service, create a knowledge base in Context Graph (Knowledge Base) and authorize it to the corresponding AI assistant service instance through Share.
For existing users of the AI Assistant service, knowledge bases previously created in the AI Assistant service will continue to be displayed as local knowledge bases on the Knowledge Base tab of the instance details page, without affecting existing usage.
Existing local knowledge bases support the following operations: browsing, editing, regenerating, and clearing knowledge bases.
Instance monitoring
On the AI Assistant service list page, click the target instance name to go to the instance details page, and then click the Monitoring tab to view the resource usage of the instance:
CPU usage: Used CPU / total specification capacity.
Memory usage: Used memory / total specification capacity.
Disk usage: Used disk space / total specification capacity.
You can select a time range to view historical trends. Data from the last 1 hour is displayed by default.
Instance logs
On the AI Assistant service list page, click the target instance name to go to the instance details page, and then click the Logs tab to query instance running logs:
You can filter log sources by subsystem.
You can search log content by keyword.
You can select a time range to filter logs.
Use the AI Assistant service
Use conversations
Use the AI Assistant service from the Web client
After the AI Assistant service instance is created, click Conversation in the instance list to start a conversation with the AI assistant directly in the DataWorks console.
Session management
The Web client supports two types of session management: regular sessions and scheduled tasks. The session sidebar on the left provides the following features:
Regular sessions:
Create a session: Click + New Task to create a new conversation session.
Switch sessions: Click a session name in the session list to switch to the corresponding session.
Scheduled tasks:
Scheduled/triggered tasks: DataWorks provides multiple built-in templates for scheduled tasks. You can select an existing template to quickly start a new task.
Conversation interaction
In the conversation interface, you can interact with the AI assistant using natural language. The AI assistant automatically calls DataWorks APIs to perform O&M operations. All write operations require your confirmation before execution.
Use the AI Assistant service from IM clients
After the AI Assistant service instance is created, you can interact with the AI Assistant service through natural language in a group where the bot is configured or in a private chat with the bot.
Proactive inquiry: In a group, @mention the bot or send a private message to it with your question or command. The AI Assistant service automatically understands your intent and performs the corresponding operation.
Scenario
Example command
Task failure diagnosis
Diagnose why task instance 12345678 failedAlert analysis
Analyze currently unresolved alertsBaseline SLA query
Check the SLA achievement of baseline base_testWorkflow backfill
Backfill workflow wf-001 for the time range 2026-01-01 to 2026-01-31Rerun failed tasks
Rerun failed scheduled instances in the abc workspace todayAutomatic alert diagnosis: When a DataWorks monitoring rule triggers an alert, the AI assistant service automatically receives the alert, performs AI-powered diagnosis, and pushes the diagnosis results to the IM group.
Tell the AI assistant service:
Enable automatic monitoring alerts and push them to the current conversation.The AI assistant service automatically configures alert listeners and sends DataWorks-triggered alert information to the current conversation as message cards. You can then use natural language commands in the chat box (such as "view failure logs", "rerun the current node", or "roll back to the previous version") to directly call underlying APIs for O&M actions without logging on to the console, reducing fault recovery time.
Enable governance inspections: You can enable automatic inspections. The AI assistant service automatically performs asset governance inspections and pushes inspection results to the IM group on a scheduled basis.
Tell the AI assistant service: Enable automatic inspections and push results to the current conversation.
Governance inspections push inspection results to the IM client at 09:30 every day by default. You can modify the push time and frequency through conversation. You can also submit more specific governance questions to the AI assistant service, such as: "Enable governance inspections and push the number of tables owned by the primary account every 3 hours" to meet personalized requirements.
Write operation confirmation: Before executing any write operation (such as rerun, freeze, delete, or modify), the AI assistant service explicitly displays the operation type, target objects, and affected quantity. The operation is executed only after you explicitly confirm it.
Scheduled tasks
The AI assistant service provides multiple built-in task templates to help you quickly configure scheduled inspection tasks. In the session sidebar of the Web client conversation interface, click Scheduled Tasks to open the template panel, and select a template to create a corresponding scheduled task session.
To configure scheduled tasks on the IM client, you can directly use natural language to instruct the AI assistant to configure them.
Scheduled inspection task templates
The following scheduled task templates are executed at 09:00 every day by default. They automatically generate inspection reports and push the reports to the conversation:
Task name | Description |
SLA baseline completion report | Diagnoses and summarizes the overall baseline completion status in the workspace for the day, and generates a report |
Workspace completion report | Diagnoses and analyzes the task completion status in the workspace for the day, and generates a report |
Inspect unhealthy assets | Summarizes governance issues under your account, analyzes priorities, and generates a report |
Inspect data quality | Summarizes high-priority tables without data quality monitoring configured, analyzes the situation, and provides suggestions |
Daily inspection of failed task root cause analysis | Summarizes failed instances from the previous day and performs in-depth diagnosis of the top 5 most frequently failed tasks |
Daily inspection of resource group utilization | Identifies resource group utilization, load, and queuing bottlenecks, and provides suggestions for scaling or staggering workloads |
Daily inspection of slow task ranking | Compares historical runtimes and analyzes the top 10 tasks with abnormally increased execution and waiting times |
Daily inspection of alert rule coverage gaps | Identifies alert coverage gaps for critical baselines and high-priority tasks, and provides suggestions for filling the gaps |
Daily inspection of backfill execution status | Summarizes backfill task statuses from the past 7 days and analyzes failure causes |
Daily inspection of tables without lifecycle configuration | Summarizes tables without lifecycle configuration by storage volume and generates top 20 configuration suggestions |
Daily inspection of ownerless tables and deprecated assets | Scans tables that have not been accessed for a long time and tables without owners, and generates a candidate decommissioning list |
Daily inspection of code change governance compliance | Check governance rule results for node changes in the last 24 hours and summarize by owner |
Daily inspection of storage and compute consumption rankings | Output the top 20 storage and compute consumers, and analyze growth trends with optimization suggestions |
Daily inspection of asset catalog coverage | Calculate the number and percentage of tables not cataloged, and provide cataloging suggestions |
Custom scheduled tasks
DataWorks also supports custom scheduled tasks. On the Web client, click Scheduled Tasks, click Create Custom in the upper-right corner of the scheduled tasks page, and follow the AI assistant's prompts to specify the task execution interval and task content.
Billing
The AI Assistant service fees include the following components:
Billable item | Billing method | Description |
Data Agent seat | Purchased by seat | A prerequisite for using the AI Assistant service. You must first activate a Data Agent seat. For more information, see Billing of the AI Assistant service. |
Resource group fees | Pay-as-you-go (by duration) | The resource group CU fees consumed by the AI Assistant service instance. If the resource group requires network connectivity, additional network fees apply: PrivateZone + private connectivity: PrivateZone (billing) and endpoint (billing). Public network access: NAT (billing). |
AI inference | Billed by token usage | The fees for the AI Assistant service calling AI models for intelligent diagnosis and analysis. For more information, see AI inference billing. |
Differences from the DataWorks agent
Comparison item | DataWorks agent | AI Assistant service |
Access entry | DataWorks console (Data Studio page) | Web client (AI Assistant service page in the DataWorks console) and IM clients (DingTalk, Feishu, and WeCom group chats) |
Primary scenarios | All scenarios including data development, data integration, and data governance | O&M scenarios (alert diagnosis, task management, baseline monitoring, etc.) and data governance scenarios |
Interaction method | DataAgent dialog box in the browser | Dedicated dialog interface on the Web client or @AI assistant in IM group chats |
Alert integration | Not supported | Supports receiving alerts and automatic AI-powered diagnosis |
Knowledge base | Not supported | Supports building a workspace-level knowledge base (RAG) |
Scheduled tasks | Not supported | Supports scheduled inspections and triggered tasks |
Custom skills | Not supported | Supports importing and managing custom skills |
AI assistant service DingTalk group
You must first click the application link to join the "Alibaba Cloud Big Data AI Platform" organization, and then scan the QR code below to join the AI assistant service DingTalk group. After joining, you can get dedicated product technical support.
