Quick BI AIPro quick start
This guide is for organization administrators and business users who are new to Quick BI AIPro. It walks you through the entire process, from activating the service to initiating your first AI-driven conversational analysis, all within 30 minutes.
Background
Traditional BI relies on data analysts to create dashboards, while business users passively consume charts. When a business question goes beyond existing reports, a new request must be submitted and scheduled for development. Quick BI AIPro deeply integrates large language model (LLM) capabilities with its core BI platform, allowing business users to drive data analysis directly through conversation. This covers the entire decision-making path: Overview → Breakdown → Root Cause → Diagnosis → Action.
Differences between Quick BI AIPro and traditional BI:
Dimension | Traditional BI | Quick BI AIPro |
Usage model | Drag and drop fields, write SQL, view static dashboards | Ask questions in natural language and conduct multi-turn follow-up inquiries |
Response time | Request fulfillment takes from days to weeks | Returns data and insights in seconds |
Analysis model | Business users rely on analysts to generate root cause conclusions | AI breaks down questions and performs automated reasoning to generate in-depth, comprehensive root cause analysis |
Analysis method | Manual drill-down, data linking, and manual creation of analysis reports | Explore and analyze through conversation, using a canvas to connect ideas and focus the analysis. Results are generated automatically. |
Learning curve | Requires SQL and BI modeling skills, familiarity with various module configurations, and a steep learning curve | No learning curve for business users |
Asset persistence | Dashboards | Analysis deliverables that update dynamically (reports, documents), one-time analysis reports, and recurring subscription tasks |
Typical use cases:
A business leader asks "What were the week-over-week sales by region last week?" five minutes before a morning meeting and instantly receives charts with root cause analysis.
An operations specialist asks "Why did GMV drop in East China?" and the AI automatically performs a three-level drill-down for root causes by category, channel, and store.
A finance specialist uses conversation to generate a "Monthly Operations Dashboard" and then sets up a recurring task to push the report on the first of every month.
AIPro workflow overview
Implementing Quick BI AIPro involves two main tracks: administrator configuration and user operation. We recommend following the order shown in the diagram below to complete the initial setup.
AIPro procedure (administrator)
The following steps are for an organization administrator or workspace developer. They cover managing users and configuring your organization's data, knowledge, and skills in AIPro to ensure a ready-to-use experience for business users.
1. User permissions
Sign in to the Quick BI Admin Center as an organization administrator.
Go to Organization Management → Role Management.
Configure AIPro-related permissions for a custom role.
NoteBy default, the preset roles in Quick BI include the necessary AIPro permissions:
The organization administrator has Centralized Management Permissions and Basic Feature Permissions by default.
The permissions administrator has Basic Feature Permissions by default.
The standard user has Basic Feature Permissions by default.
On the Member Management page, assign roles with AIPro permissions to members as needed.
2. Connect enterprise data
Goal: Allow business users to find and use your organization's predefined data, including data tables, datasets, files, and API data assets.
Create data source and dataset resources in a workspace.
As an administrator, go to a Quick BI workspace.
Create a data source: In the workbench, go to Data Sources and add a database connection (such as MySQL, MaxCompute, PostgreSQL, or Oracle).
Create a dataset: In the workbench, go to Datasets and configure a dataset.
In Workspace Management, grant permissions for the dataset to the required members or roles.
Create file, data table combination, and API data resources in AIPro.
Go to AIPro > Enterprise > Data Management.
Create data table combinations, files, and API data.
Select a data resource, click More, and grant collaborative permissions to users.
3. Pre-configure common data assets (optional)
Goal: Enable business users to see commonly used departmental data assets immediately after they sign in, without needing to configure or search for data sources.
As an administrator, go to Admin Center → Pre-configured Data Assets (path:
ai/org/pre-asset).Select "New Asset Package" to configure the datasets or data tables to recommend to business users.
After saving, business users will see these data assets prioritized when they type @ in the conversation input box.
4. Configure knowledge center
Goal: Populate the knowledge center with your organization's business definitions, metric definitions, and field descriptions. This ensures that AI analysis results align with your company's standards.
Go to Admin Center → Knowledge Management (path:
/ai/org/knowledge).Click "Add Knowledge" to create knowledge that contains business logic.
Click Smart Import to parse and learn business logic from documents and import it as enterprise knowledge.
After saving, the AI will retrieve and reference this knowledge during conversations about datasets.
5. Configure skills (optional)
Goal: Transform standard analytical frameworks and methods (such as monthly business reviews, anomaly root cause analysis, or store performance dashboards) into reusable AI skills.
Go to Admin Center → Skill Management (path:
/ai/org/skill).Click Add Skill and upload the skill's ZIP package.
Set the skill's Visibility (all users / specific users).
After saving and publishing, business users can find and use the skill in Enterprise → Skill Square. They can also call the skill by typing
/in the conversation input box.
6. Connect MCP connectors (optional)
Goal: Integrate external tools (such as DingTalk, Feishu, internal APIs, or industry data sources) into the AI analysis workflow through the MCP (Model Context Protocol) to extend analytical boundaries.
Go to Admin Center → MCP Management (path:
/ai/org/mcp).Click Add Connector and enter the configuration information for the MCP.
Set the connector's visibility and invocation permissions.
Business users can enable and invoke the connector from Enterprise → MCP Square during a conversation.
7. Credit and quota management
Goal: Control and audit resource usage by users across the organization.
Go to Organization Management → Credit Management (path:
/org/admin/creditManage).View the Credit balance and consumption details for users in your organization.
8. Configure AIPro management permissions
Goal: Ensure data visibility and operational permissions comply with corporate governance requirements. You can grant users AIPro administrator privileges by using a custom role.
Go to Admin Center → Organization Management → Role Configuration (path:
/org/admin/user/role).Quick BI AIPro provides the following preset roles:
Role | Primary permissions | AIPro admin capabilities |
organization administrator | Manages the entire organization | Yes |
workspace administrator | Manages members, data assets, deliverables, and subscriptions within a workspace | No |
workspace developer | Creates datasets, reports, and skills, and publishes assets to the enterprise | No |
custom role | Can help the organization administrator manage AIPro capabilities if granted the required permissions. | Yes |
AIPro procedure (user)
This section is for business users who have been assigned an AIPro seat. Follow these steps to complete your first AI-driven conversational analysis.
1. Sign in to AIPro
Sign in to Quick BI with your Alibaba Cloud account.
In the top navigation bar, click AIPro to go to the AIPro homepage.
The homepage displays two view tabs, "My" and "Enterprise", and defaults to the "My" view.
2. Configure data assets
Go to My Data.
Add data: You can add enterprise data from the Enterprise Data Square or upload your own local files. Supported file types include Excel, PDF, Word, Markdown, and TXT.
Data processing: After you add data, the AI takes 1–2 minutes to process it. Once complete, go to New Task to begin your analysis.
3. Ask questions in natural language
Go to New Task and enter your analysis question in the input box. Examples:
"Month-over-month sales changes by region for this month"
"What are the main reasons for the GMV decline in the East China region?"
"Generate a business analysis report for Q2 2026"
AIPro also supports multi-turn follow-up questions. For example:
"Show sales for each category in June."
"Which are the top 5 fastest-growing categories?"
"Review the reasons for this growth."
After you submit the question, the AI returns structured results such as charts, tables, and written conclusions.
4. Get analysis results
The system generates analysis results based on your question.
Charts and narratives: Retrieves data and presents it visually.
HTML reports: Present analysis conclusions visually. This format is often used for one-time exploratory analysis and personalized report creation.
Analysis reports: Supports dynamic updates, filtering, and interactive drill-down analysis. This format is ideal for scenarios that require regular data refreshes and data sharing within an organization.
Document reports: Generates document-style analysis results based on charts and narratives, with a high degree of editing flexibility.
5. Use analysis results
Share: You can share conversation results either privately or publicly and configure an expiration date for the share link.
Save: For documents and analysis reports, click Save to My Analysis in the upper-right corner to save the results to your personal library of deliverables.
Subscribe: Set up subscription tasks through conversation. AIPro runs them on a schedule and pushes the latest results. You can manually modify the delivery frequency and channel.
Download: You can download HTML reports and document reports as local files.
Module reference
Quick BI AIPro consists of the following modules, covering the entire workflow from personal use to enterprise assets and administrative configuration.
View | Module | Description | Primary users |
My | New Task | Drives AI analysis using natural language to produce charts, reports, and presentations | business user |
My | My Analysis | Saves personal analysis deliverables, supporting further editing and sharing | business user |
My | My Subscriptions | Manages scheduled push tasks, supporting multi-channel distribution | business user |
My | My Data | Manages personally uploaded data files and data assets | business user |
Enterprise | Data Square | Browse the organization's available datasets, data tables, files, and API data | All users |
Enterprise | Skill Square | Browse and enable the organization's published skills for use in conversations | All users |
Enterprise | MCP Square | Browse and enable the organization's integrated MCP connectors to extend AI analysis boundaries | All users |
Admin Center | AIPro Management | Configure data, knowledge, skills, and MCP connectors | organization administrator, roles with AIPro management permissions |
Admin Center | Role Configuration | Manage organization roles and permissions | organization administrator |
Organization Management | Credit Management | View Credit balance and consumption details | organization administrator |
More capabilities
After you have completed the basic configuration and your first conversation, you can explore the following advanced capabilities:
Canvas: Drag and drop charts, tables, and conclusion cards from multiple conversations onto a canvas. Freely arrange and combine them to create a thematic analysis board. The canvas can be exported as an HTML snapshot, a report, or a presentation.
Scheduled subscriptions: Convert any analysis result into a subscription task. Choose a delivery frequency (daily, weekly, monthly, or a Cron expression) and a delivery channel (email, DingTalk, Feishu group, or webhook). The AI will periodically execute the analysis and push the latest data snapshot.
Presentation generation: Generate a PPTX presentation file based on the analysis results of your data assets, which can be used directly for business reports.
FAQ
Q1: I can't see the AIPro entry point after I sign in. Why?
Ensure your user type is set to "developer" or "analyst". Contact your organization administrator to have the correct seat assigned.
Q2: The data list is empty when I type @ to select data. Why?
Make sure you have added at least one data asset to My Data and that it has finished processing.
Q3: The conversation shows an "Insufficient quota" message. Why?
Your personal monthly Credit has been exhausted. Contact your organization administrator to request an additional quota, or wait for the next billing cycle.
Q4: The results returned by the AI do not match our business definitions. What should I do?
You can ask an administrator to configure enterprise knowledge. If you are satisfied with the results, you can ask an administrator to promote your personal knowledge to enterprise knowledge.
Q5: How can I automatically push analysis results to my email or DingTalk?
In My Subscriptions, enable Push to Specified Users and configure the recipients.
