teableio · HynLcc · May 7, 2026 · May 6, 2026 · May 7, 2026
diff --git a/docs.json b/docs.json
diff --git a/en/basic/ai/ai-chat.mdx b/en/basic/ai/ai-chat.mdx
@@ -5,62 +5,108 @@ description: Interact with your data using natural language for analysis, visual
 
 <Note>Available on all Cloud plans; Self-Hosted requires Business or higher.</Note>
 
-Teable's AI Chat reads the context of the page you're on and helps turn questions about data into directly usable results. It works well for analyzing tables, generating charts, following up with more questions, and handling more complex agent tasks with context.
+AI Chat helps analyze the current table, explain record content, generate temporary charts, and create or update tables, views, apps, and automations.
+
+AI prioritizes the current page. To reference other tables, views, apps, automations, or folders, type `@` in the input box and select the related node.
 
 ## How to Open
 
-Click the **Cuppy** icon in the top right corner to open AI Chat from any page.
+Open a table or view, then click the **Cuppy** icon in the top right corner to open AI Chat. Describe the question or task in the input box. If the task will modify data or create nodes, ask AI to list the plan first, then confirm before execution.
+
+## What AI Can Reference
+
+AI prioritizes information from the current page:
+
+- **Current table and view**: The current table, current view, and the filtered or sorted results in that view.
+- **Selected records**: If records are selected, AI uses them as key context.
+- **Uploaded files**: Add PDFs, Excel files, Word documents, images, and other files to the conversation.
+- **More nodes with `@`**: Type `@` in the input box to add tables, views, apps, automations, or folders from the tree.
+
+Files can also be pasted or dropped directly into the input box. They appear as attachment chips first, then become available to AI after the message is sent.
+
+## Common Uses
+
+<CardGroup cols={2}>
+  <Card title="Create tables and automations" icon="sitemap">
+    Plan a business database, create tables, views, apps, automations, or update existing records.
+  </Card>
+  <Card title="Analyze data" icon="chart-line">
+    Summarize data in the current table or view, or analyze across multiple related nodes.
+  </Card>
+  <Card title="Temporary charts and reports" icon="chart-pie">
+    Generate one-time chart or report previews from queried data.
+  </Card>
+  <Card title="Read files" icon="file-lines">
+    Answer questions using PDFs, Excel files, Word documents, images, and other attachments.
+  </Card>
+</CardGroup>
+
+### Create Tables and Automations
 
-## Context Scope
+AI Chat can help create, update, and organize data, not only answer questions. For a new business workflow, discuss the data structure first, then ask AI to create the tables, views, apps, and automations.
 
-AI Chat automatically reads the current context, including:
+Suitable prompts include:
 
-- **Current table and view**: It prioritizes the table, view, and filtered result set you are currently looking at.
-- **Selected records and attachments**: Selected data and uploaded files on the page are included too.
-- **Manually added context**: If you need to ask across tables, you can add related tables into the context first.
+- Help me plan a customer follow-up system. What tables and fields do I need?
+- Based on the plan above, create these tables, views, and fields.
+- Add priority, assignee, due date, and status fields to the task table, then create common views.
+- Change the selected records to Completed.
+- Create a new table from this Excel file and check whether the field types are appropriate.
+- Create a CRM app from this customer table, with customer list, customer detail, and follow-up record pages.
+- When a new order is created, notify the owner and include the order number, customer name, and amount.
 
-## Capabilities
+For a complete business database, start by asking AI to plan the table structure. After reviewing the plan, continue with table, view, app, and automation creation.
 
-### 1. Deep Data Analysis (Text-to-SQL)
+<Steps>
+  <Step title="Plan first">
+    Describe the business goal, such as building a customer follow-up system, and ask AI to outline the required tables, fields, views, and automations.
+  </Step>
+  <Step title="Confirm the structure">
+    Review the proposed tables, fields, field types, and relationships. Add any missing rules or workflow details.
+  </Step>
+  <Step title="Create next">
+    Ask AI to create the confirmed tables and views, then continue with apps or automations.
+  </Step>
+</Steps>
 
-Teable's AI Chat does more than guess. It works like a data analyst that can turn your request into a real query.
+For app creation details, see [App Builder](/en/basic/ai/app-builder). For automation details, see [Automation](/en/basic/automation).
 
-- **SQL Generation**: It converts your natural language questions into complex, executable SQL queries.
-- **Precision**: Because it executes code against your database, results such as counts, sums, and averages are 100% accurate.
-- **Complex Logic**: It can handle grouping, filtering, and cross-table references.
-  - *"Which product category had the highest growth rate QoverQ?"*
-  - *"List customers who haven't placed an order in the last 6 months but have a balance > 0."*
+### Analyze Data
 
-### 2. Charts and Visualization
+Ask questions about data in the current table, for example:
 
-- Bar, line, pie, scatter, and area charts are all supported.
-- You can keep refining a chart through chat, such as *"Switch to a stacked bar chart"* or *"Group by region"*.
-- For more complex presentation needs, you can first ask AI Chat to shape the data into a chart-ready format.
+- Count completed tasks this month by assignee.
+- Find the customers with the highest sales in the past 30 days.
+- Analyze unusual records in this view.
 
-### 3. Smart Agent
+If the question involves multiple tables, use `@` to add the related tables or views to the conversation.
 
-AI Chat does not only answer questions. It can also help you move the next step forward.
+### Generate Temporary Charts or Report Previews
 
-- **App Builder**: Start creating apps directly from the conversation.
-- **Automation**: Describe a workflow and let AI help configure triggers and actions.
-- **Scripts**: Ask AI to generate more specific JavaScript for your use case.
+AI can generate one-time HTML previews from queried data, useful for checking charts or reports quickly:
 
-### 4. Read Files and Web Pages
+- Generate a weekly sales trend chart.
+- Turn this query result into a pie chart.
+- Create a summary report from these records.
 
-If you upload files, or if the selected model supports web search, AI Chat can use that content alongside your data.
+<Info>
+These previews are not saved as long-term apps and do not refresh data automatically. For dashboards, business pages, or interactive apps that need to be reused, create an app with [App Builder](/en/basic/ai/app-builder).
+</Info>
 
-- Supports PDFs, Excel files, Word files, images, and other attachments.
-- Can answer by combining document content with table data.
-- If the current model has web search enabled, AI Chat shows web results together with source links.
+### Read Files
 
-## Good Times to Start a New Chat
+After uploading files, AI can answer questions using both file content and table data:
 
-- The topic has changed.
-- The current conversation has become too long and the result starts drifting.
-- You want to reduce the extra compute cost caused by too much previous context.
+- Summarize this PDF and connect it with the current customer record.
+- Read this Excel file and identify the fields that should be imported.
+- Generate a product description from this image.
 
-## Best Practices
+## Prompting Tips
 
-- **State the goal clearly**: Instead of saying "Analyze this," say something like "Analyze weekly sales trends over the past 3 months."
-- **Use field names when possible**: For example, "Sort by `Created Time`."
-- **Start a new chat when the topic changes**: A new chat is usually more stable and uses less compute.
+- **State the goal first**: In the first message, describe what to do, the relevant conditions, and the expected output. For example, analyze weekly sales trends over the past 3 months, grouped by region, and return a trend table with a short conclusion.
+- **Use field names**: For example, sort by `Created Time`, so AI can identify the target column.
+- **Provide several examples**: For fixed-format output, provide 3-5 input -> expected output examples.
+- **Use `@` to select nodes**: When AI needs to reference tables, views, apps, automations, or folders, type `@` and select them directly.
+- **Confirm before execution**: For tasks that modify data, create tables, create apps, or enable automations, ask AI to describe the changes before running them.
+- **Choose the model by task**: If the space supports model selection, use a lighter model for simple queries, cleanup, or rewriting, and a stronger model for complex planning, cross-table analysis, and app building.
+- **Start a new chat when the topic changes**: A new chat is recommended when the topic changes, the conversation becomes too long, or context usage should be reduced.
diff --git a/en/basic/authority-matrix/authority-matrix-practical-guide.mdx b/en/basic/authority-matrix/authority-matrix-practical-guide.mdx
@@ -1,5 +1,5 @@
 ---
-title: "Authority Matrix Practical Guide"
+title: "Authority Matrix Guidelines"
 ---
 
 <Tip> Think of the Authority Matrix as a powerful tool. It lets you build precise data access rights for each role on your team, just like assembling building blocks. Don't worry if it seems complex; we'll walk you through a common scenario step by step. </Tip>
@@ -145,4 +145,4 @@ Now, let's configure granular permissions for each role. We have three tables: `
 > -   **Full Visibility**: When he opens the `Customers` table, he can see every customer in the company, giving him a complete overview for analysis and team reviews.
 > -   **Complete Security**: When he double-clicks a record owned by another rep, he'll see that all fields are read-only (often grayed out and uneditable). There are no "Save," "Edit," or "Delete" buttons available. This completely eliminates the risk of accidental changes, allowing him to browse and present data with confidence.
 >
-> ![The Sales Rep's view with added viewer permissions](/images/2025-08-02-18-31-53.gif)
+> ![The Sales Rep's view with added viewer permissions](/images/2025-08-02-18-31-53.gif)
diff --git a/en/basic/authority-matrix/authority-matrix.mdx b/en/basic/authority-matrix/authority-matrix.mdx
@@ -1,5 +1,5 @@
 ---
-title: "Authority Matrix"
+title: "Overview"
 description: "Allows administrators to set fine-grained access permissions for team members. Through this approach, precise control over different tables, fields, and operations can be achieved, ensuring each member can only access and modify information within their scope of responsibility. This not only improves team collaboration efficiency but also enhances data security."
 ---
 
@@ -63,4 +63,4 @@ After modifying table permissions, you must click the switch to the left of the
 - After enabling the authority matrix, the creation, editing, and deletion permissions of fields (columns) themselves are only available to administrators.
 - Once the Authority Matrix is enabled, only users with "Manager" permissions are exempt from its restrictions. For permission levels below "Manager" (such as "Creator" and below), all members except Authority Matrix administrators are subject to the Matrix's unified control.
 
-<Note>To learn about basic permission levels for spaces and bases, please refer to [Collaboration Permissions](/en/basic/space/space-permission)</Note>
+<Note>To learn about basic permission levels for spaces and bases, please refer to [Collaboration Permissions](/en/basic/space/space-permission)</Note>
diff --git a/en/basic/automation.mdx b/en/basic/automation.mdx
@@ -1,6 +1,6 @@
 ---
 title: "Overview"
-description: "Teable Automation makes powerful workflows simple with plain-language AI setup."
+description: "Create automation workflows with AI or manual configuration."
 ---
 
 Teable Automation makes powerful workflows simple. No code, no drag-and-drop, no complicated setup. Just tell AI what you need in plain language, and Teable takes care of the repetitive work for you.

diff --git a/en/basic/automation/actions/logic/http-request.mdx b/en/basic/automation/actions/logic/http-request.mdx
@@ -105,7 +105,7 @@ After the HTTP request runs, the response is available to subsequent actions:
 - **Status code** — the HTTP status (200, 201, 404, etc.).
 - **Response body** — the data returned by the API, parsed as JSON if applicable.
 
-You can reference specific fields from the response using the **+** variable picker in later steps. For example, if the API returns `{"id": "abc123", "status": "created"}`, you can reference `id` and `status` individually.
+You can reference specific fields from the response using the **+** variable picker in later steps. For example, if the API returns `{"id": "abc123", "status": "created"}`, you can reference `id` and `status` individually. When inserting dynamic values with **+**, you can also use field paths and formatting options when an external API requires a specific request format.
 
 This is useful for chaining API calls — for example, create something via POST, get back an ID, then use that ID in a subsequent Update Record or another HTTP request.
 

diff --git a/en/basic/base/base.mdx b/en/basic/base/base.mdx
@@ -1,5 +1,5 @@
 ---
-title: "Base"
+title: "Overview"
 description: "Create, manage, import and export bases. Move data between Teable Cloud spaces or migrate between Cloud and Self-Hosted instances using .tea files."
 ---
 

diff --git a/en/basic/field/ai/ai-field.mdx b/en/basic/field/ai/ai-field.mdx
@@ -134,3 +134,7 @@ Combine multiple fields and your own prompt to generate the result you want.
 />
 
 <Tip>In addition to Teable's built-in models, Teable also supports [third-party model APIs](/en/basic/ai/custom-model), which you can configure in space settings.</Tip>
+
+### Generate Image
+
+Attachment fields can use **Generate Image** to create images from text fields, attachment fields, or a combination of both.