Say goodbye to tedious data grunt work. DataWorks features a built-in AI assistant that understands your needs: DataWorks Copilot. DataWorks Copilot is designed to free you from repetitive, inefficient work, giving you back valuable time for innovation and critical thinking. It makes data development simple and efficient again. Deeply integrated with DataWorks, you can use natural language to ask Copilot to:
Generate code: Instantly transform your ideas into high-quality, standardized code.
Automate Task creation: Automate data development and governance Tasks to build your workflows.
Share team knowledge: Incorporate best practices and business knowledge as Context into every interaction.
Overview
What is DataWorks Copilot
DataWorks Copilot is the intelligent assistant for DataWorks, the one-stop platform for intelligent data development and governance. Powered by AI reasoning and Natural Language Processing, it helps developers use natural language prompts to quickly perform various code-related tasks. These tasks include generating, completing, refactoring, optimizing, and explaining SQL and Python code, as well as code debugging and test case generation. As an intelligent engine for data development, DataWorks Copilot understands your business needs through Context. Enhanced by your enterprise-specific Knowledge Base, it helps you easily complete data ETL and data analysis Tasks.
DataWorks Copilot provides three core capabilities: the Agent, the Coding Assistant, and Quick AI Operations. These are deeply integrated into various DataWorks modules to provide a new, intelligent data work experience.
Core value
Increase efficiency: Significantly shorten data development and analysis cycles through automated code generation, intelligent code completion, and natural language interaction.
Lower the barrier to entry: Lets users who are unfamiliar with complex SQL or product operations quickly complete data development and governance Tasks using natural language.
Ensure quality: Use AI for code debugging, code optimization, and test case generation to improve code quality and maintainability.
Preserve knowledge: Incorporate company standards, business definitions, and technical specifications into the AI through a custom enterprise Knowledge Base, enabling knowledge sharing and application.
Availability and policies
Eligible users: Available to customers with DataWorks Basic Edition or higher. Some features are available only in the new version of Data Studio.
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), and Japan (Tokyo).
Current phase: Full public preview. The Tenant Administrator or a user with equivalent permissions can enable Copilot. To do so, click the Copilot entry point, carefully read the DataWorks Copilot Terms of Service, and click Confirm Participation. Once confirmed, all users under the Alibaba Cloud account can use Copilot.
Billing: During the public preview period, DataWorks Copilot is completely free. It will transition to a paid service after the public preview ends.
ImportantDataWorks Copilot is scheduled to begin commercial billing on April 1, 2026. The specific billing plan will be announced on the official website before the commercial launch.
Get started
How to access Copilot
You can interact with Copilot in the following ways:
Global entry point: Click the Copilot icon in the upper-right corner of the DataWorks interface to open the Copilot chat dialog.
In the editor: In the intelligent code editor for code-based data development nodes, open Copilot from the right-click menu or with a keyboard shortcut.
Embedded in modules: Use the quick operation buttons marked with the Copilot logo in the functional areas of specific product modules.
Main interface overview
From the global entry point, Copilot provides pre-built scenario-based examples (such as Data Synchronization, intelligent table discovery, Data Development, and Data Governance). You can click the corresponding card to quickly load a sample prompt for that scenario, making it easier to get started.
Core features
Agent: Automate complex tasks
Overview
The DataWorks Agent service ushers in a new era of automation for data development and data governance. It goes beyond simple Q&A to become an intelligent agent that can complete complex Tasks autonomously.
With the DataWorks Agent, you can use natural language to automate parts of your data development and governance work in DataWorks, including Data Integration, Data Development, Data Map, and Data Governance. Leveraging the deep reasoning and planning capabilities of a Large Language Model (LLM), the Agent can fully understand your Task, break it down into steps, create an execution plan, and use the relevant tools in the MCP Server to automate execution. DataWorks will continue to enrich and iterate the toolsets in the DataWorks MCP Server to provide a more intelligent and efficient product experience for data development and governance.
Key features
Deep understanding and autonomous planning: Accurately identifies complex intent through Context awareness and multi-turn dialogue, and independently breaks down Tasks into multi-step, executable plans.
Automated data development and governance: Deeply integrates with core DataWorks product capabilities and processes, fully connects contextual data, and includes a built-in DataWorks toolset.
How to access
In the Copilot chat dialog, switch from Ask mode to Agent mode.
Based on your Task type, enter
/to select the appropriate Agent type.Instruct the Agent with a prompt.
Use cases
Use case 1 - Data Studio Agent
Description: Provides a natural language-based ETL development experience, covering the complete workflow from requirements analysis, Code Generation, and Workflow generation to publishing.
Use case 2 - Data Integration Agent
Description: You can describe your data synchronization needs directly in natural language (such as Chinese or English). The system automatically parses the semantics and intelligently generates the corresponding Data Synchronization Task configuration, including source and destination data source types, table schema mappings, field filtering conditions, partitioning strategies, and scheduling parameters.
Use case 3 - Data Map Agent
Description: Focuses on improving the efficiency of data discovery and understanding. Through AI-driven natural language interaction, you can quickly explore metadata in various scenarios across massive datasets.
Core capabilities:
Natural language search: Supports natural language Q&A. You can quickly locate target data based on business intent without needing precise keywords. For example, "Find the summary table related to user activity."
Automatic scope adjustment: Supports specifying a scope in the conversation. The Agent will automatically understand the semantics and quickly locate data within that scope. For example, "In the adm_bi project, find tables related to business operations."
In-depth data understanding: Supports follow-up questions about target data to quickly obtain detailed information such as data lineage, owner, and field definitions. For example, "What are the direct downstream dependents of the @dws_bi_metric_di table? Who would be affected by a change?"
Use case 4 - Data Governance Agent
Description: The DataWorks Data Governance Agent shifts enterprise data governance from a proactive to an autonomous model. Instead of performing complex analysis and filling out forms, you can use natural language commands, which are translated into precise governance actions. These actions are then configured with expert-level governance capabilities and can be executed automatically.
Core capabilities:
Quality Rule configuration: Use natural language to automatically configure monitoring rules for specified key tables. The Data Governance Agent can intelligently analyze a table's field types, business semantics, and importance to automatically recommend and configure appropriate monitoring rules, such as primary key uniqueness, NOT NULL constraints, and allowed-value validation. This efficiently completes work that would otherwise require extensive data exploration and rule configuration.
Example: Automatically generate quality rules for the core user dimension table
dim_user_info.Example: Automatically configure table row count quality rules for tables starting with
ods_.
Quality issue resolution: For quality issues automatically identified by the system in the data asset governance module, such as "Frequently accessed tables without quality rules" or "Tables produced by high-priority tasks without quality rules," you can directly provide governance requirements in natural language. The system automatically analyzes and resolves the issue.
Example: Find frequently accessed tables that have no quality rules, then recommend and configure quality rules for them.
Example: Help me resolve the data quality issues.
Use case 5 - Data O&M Agent
Description: Provides comprehensive health assessment and issue diagnosis for Task Instances. By analyzing multiple dimensions such as dependency chains, resource levels, historical run trends, change impacts, log exceptions, and data quality, it automatically generates a structured diagnosis report.
For more information about the Data O&M Agent, see AI-powered O&M.
Coding assistant
Overview
The DataWorks Copilot Coding Assistant, built on an advanced Large Language Model, efficiently handles tasks like generating, optimizing, explaining, and testing SQL/Python code through natural language interaction. For the best results, you can freely switch between various models such as the DataWorks default model, Qwen, and DeepSeek, significantly improving the efficiency of ETL development and data analysis.
Key features
Flexible model switching: Supports the default model, Qwen3-235B-A22B, and more.
Full-link ETL support: Supports code generation, Q&A, refactoring, optimization, debugging, comment generation, test case generation, and explanation for both SQL and Python.
Context awareness: Understands conversational content, code, table schemas, data lineage, and custom knowledge bases.
How to access
Intelligent code editor
Scenario 1: Intelligent code completion
How to use: While developing a code-based node, Copilot intelligently predicts and recommends subsequent code snippets based on the Context (such as entered code and referenced table schemas). The completion suggestion appears automatically; press Tab to accept it.
Scenario 2: Right-click menu quick operations
How to use: In the intelligent code editor, select the desired code, right-click, and choose Copilot from the menu that appears.
Copilot Chat (Ask mode)
Ask mode is the default mode for Copilot Chat and is suitable for solving specific coding problems in a Q&A format. You can perform code generation, code refactoring, code debugging, comment generation, code explanation, code optimization, code testing, code Q&A, intelligent Notebook cell generation, and quick table discovery. When using Copilot Chat in Ask mode, you can select code in the editor to use as context for your request.
Use cases
Use case 1: Generate ETL scripts
Description: You can express your business requirements in natural language, and DataWorks Copilot will automatically convert the natural language command into a SQL or Python statement.
Example: "Based on the dwd_ec_trd_create_ord_di table, calculate the sales, sales volume, SKU count, buyer count, and seller count for each SPU from September 1, 2024, to September 18, 2024."
Use case 2: Auto-complete code
Description: The DataWorks Copilot code completion feature can intelligently complete the SQL you are writing.
Example: No command is needed. Suggestions are generated automatically. Press the indicated key to accept.
Use case 3: Refactor code
Description: You can modify existing code using natural language. Simply state your requirement, and DataWorks Copilot will refactor the specified code.
Example: "Modify the sql to transpose its result from columns to rows using unpivot."
Use case 4: Find and fix code errors
Description: In DataWorks, you can proactively check for errors in your code before execution. If the code fails after running, you can also use one-click debugging to fix the error. DataWorks Copilot explains the error and provides the corrected code.
Example: Select the code, right-click, and choose the quick command.
Use case 5: Explain code
Description: DataWorks Copilot can explain your specified code, which improves readability and helps you understand it quickly.
Example: "Explain this SQL."
Use case 6: Add code comments
Description: DataWorks Copilot can generate comments for specified code, improving its completeness and readability.
Example: "Add a comment for each field."
Use case 7: Answer SQL questions
Description: You can ask questions about SQL syntax or MaxCompute functions in natural language. DataWorks Copilot will provide explanations and usage examples to help you deepen your understanding.
Example: "How do I write a mapjoin in MaxCompute?"
Use case 8: Optimize code performance
Description: In the DataWorks Copilot chat window, you can initiate SQL optimization for specified code, such as using a JOIN to combine multiple tables. This simplifies the code logic, improves runtime efficiency, and can reduce the load on the database.
Example: Select the code and use the quick command in the dialog box.
Use case 9: Generate test cases
Description: In the DataWorks Copilot chat window, you can generate test cases for specified code. DataWorks Copilot will generate a complete code testing report that covers multiple aspects, including unit tests, code performance, and boundary condition validation. It also generates test code to verify that each part of your Task code works as expected.
Example: "Generate SQL test cases and explain the testing steps."
Quick AI operations
Modules such as Data Development, O&M, and Data Quality in DataWorks leverage the power of LLMs to provide convenient and intelligent product operations. This offers an intelligent product experience that helps developers and enterprise users complete DataWorks operations efficiently.
Visualize query results
Description: In DataWorks Data Development and Data Analysis, you can use the DataWorks Copilot intelligent chart assistant to generate visual charts and data insights from your query results with a single click.
How to access: In the node run or SQL query results, switch to the visualization tab.
AI-powered table creation
Description: In the Data Studio data catalog, you can use the DataWorks Copilot table creation assistant to create a table just by entering a keyword for the table name. You can also trigger it with one click to get intelligent recommendations for field names and descriptions.
How to access:
Generate release descriptions
Description: In Data Studio, during the publishing process, you can use the DataWorks Copilot publishing assistant to generate a release description with one click, improving publishing efficiency.
How to access:
Diagnose task exceptions
Description: The Intelligent Diagnosis in DataWorks Operation Center now officially integrates with the Qwen and DeepSeek-R1 (671B) models. When a Task fails, click Perform Diagnostics. The LLM can extract key information from the logs in seconds, provide an error analysis and solution suggestions, and recommend quick operations to fix the error, helping to automate O&M.
How to access: On the Operation Center page, click in the left-side navigation pane. On the Auto Triggered Instances page, click a failed Instance, select the failed node, and then click Perform Diagnostics in the lower-right corner to diagnose the Task.
Recommend data quality rules
Description: You can use Copilot with a single click to quickly generate a quality rule suitable for a specific data table or business scenario, based on the complete metadata in DataWorks. This supports multiple data source types and multi-dimensional quality checks.
How to access: On the Data Quality page, click in the left-side navigation pane. On the Configure By Table page, select a target table and click Create Monitor on the right to configure the quality rule for that table.
DataService API
Description: DataWorks DataService can use the Copilot intelligent assistant for quick API encapsulation. It can generate a SQL script based on business requirements with a single click and automatically parse it into API request and response parameters.
How to access: In the DataService Studio module, create a new API and select code editor.
Advanced features and best practices
Improve response accuracy
To better align Copilot's responses with your enterprise standards and business scenarios, we highly recommend providing it with specific context.
Custom knowledge (rules)
Description: Rules are a series of guidelines, specifications, and background knowledge you define for Copilot. They guide Copilot's thinking and responses.
How to access: In the Copilot chat window, click the
icon in the upper-right corner to go to the Rules configuration page.Enterprise-level and Personal-level Rules:
Enterprise-level Rules: Configured by an administrator and can be applied to a specific scope. Ideal for defining company-wide business terms, coding standards, and more.
Personal-level Rules: Configured by individual users and only apply to them. Ideal for defining personal preferences, frequently used code snippets, and more.
Specify conversation context
Description: In each conversation, you can manually specify the Context related to the current Task. This allows Copilot to focus on that information when generating a response, resulting in a more accurate answer.
Supported Context types:
Table: Reference the metadata of one or more tables.
Node/Code file: Reference the code within a specific node.
Data collections: Reference data collections from Data Map.
Rules: Temporarily apply one or more Rules to the current conversation.
Local file: Upload a local document to use as background information.
How to reference Context: In the Copilot chat input box, type
@or click+to open the context selector and add items.
Manage your conversations
View conversation history
Copilot automatically saves your recent conversations.
Record scope: You can view up to 100 conversations from the last 7 days.
How to access: Click History in the upper-right corner of the Copilot chat window.
Best practice: Start a new chat per task
We highly recommend that you start a new chat for each separate Task.
Reason: This prevents the contexts of different Tasks from interfering with each other, which allows Copilot to focus on the current Task and ensures the accuracy and relevance of its answers.
FAQ
Q: Why are Copilot's answers inaccurate or not what I expected?
A: The most common cause is a lack of context. Try providing more specific background information using the methods described in Specify conversation context.
Q: What is the difference between Ask mode and Agent mode? How should I choose?
A: Ask mode is suitable for simple, single-step tasks like generating a code snippet or explaining a function. Agent mode is designed for complex Tasks that require multiple steps and the use of various tools.
Q: How can I make Copilot reply in English by default?
A: Use either of the following approaches:
When asking a question, explicitly add an instruction, such as
Please answer in English,Respond in English, orExplain in English.Switch to the DataWorks English interface to improve the consistency and accuracy of the model's English output.