Bubble AI Agent
The Bubble AI Agent
The Bubble AI Agent is an in-editor assistant that helps you build, troubleshoot, and understand your app more efficiently. It’s trained on Bubble documentation and provides hands-on guidance so you can spend less time searching for answers and more time building. You can also prompt it to create and modify simple UI elements.
How to access the AI Agent
The Agent opens automatically the first time you load your app — there’s nothing to install or activate. You can minimize it at any time and reopen it by clicking the magic wand icon in the top navigation bar: 
. The window is resizable and responsive, and it remains open until minimized 
. You can keep it visible while working in the editor or hide it when you prefer a cleaner workspace.
What the AI Agent can do
The AI Agent assists in three key areas:
It’s multilingual — you can prompt it in your preferred language, and it will respond in the same language.
The Agent supports you in building, understanding, and learning within Bubble — from making visual edits to explaining how your app works.
If you click on any part of your app, the Agent automatically gets the context of what you’ve clicked on, so it will give higher quality output in all three key areas listed above. We highly encourage you to click on a part of your app (hold down shift to select multiple elements) when you want to make changes to it or learn more about it.
You have full control here – remove the context by clicking “x” next to the relevant icon within the chat:
UI creation and modification
The Agent can create or modify your app’s design, including:
Full pages – you can prompt to create a new page
Specific sections like headers, navigation bars, or footers
Individual components such as groups, images, text, and buttons
You’ll get the best results when prompts are specific about what to change and where.
When the Agent creates elements, it follows design best practices:
All elements are responsive by default
Layouts are well-organized with logical parent-child relationships
Proper margins and padding are applied
App style variables are respected for consistent design
After you prompt UI creation and modification, the Agent will present a plan to you that you can either approve or cancel. Click approve and the changes will instantly be made.
Dynamic expressions
The AI Agent automatically creates or edits dynamic expressions based on your prompt. When you ask it to make a change, it searches your app for the right data sources and operators needed to complete the task. It then summarizes the updates it plans to make so you can review and approve them.
You might have a repeating group which contains a list of all tasks completed by all users, and you want to show tasks completed by the current user. Example prompt: After selecting the repeating group to give the AI Agent context, you can prompt: “Can you generate an expression for this repeating group that searches for a list of tasks completed by the current user?”
If you have a task management system, you can display who completed a task by adding a text element to the cell. Example prompt: “Edit this expression to also include the email address of the user who completed the task.”
Current limitations: this version can’t incorporate conditionals, and it can’t leverage data sources from API calls, since plugins aren’t currently supported by Bubble AI.
Data type generation and modification
The AI agent can generate new data types and modify existing data types and their accompanying fields. We recommend using the Agent over the data type generation tool on the Data tab because it’s able to modify existing fields as well.
Create new data types (collapsible header)
Say you're building a gym management app. You might need to add additional data types beyond what was initially generated, like a Gym data type.
You can prompt: "Add a Gym data type with fields: Name (text), address (text), capacity (number), opening_hours (text).”
IMAGE TK
Generate data types from existing elements (collapsible header)
When you're building new UI elements that need data, the Agent can create the types and fields automatically. Say you’re creating a new registration form in your gym management app (make sure to select the form UI to give the Agent context):
Prompt: "Create the correct data field entries for all the elements in the parent registration form."
IMAGE TK
Modify existing data types (collapsible header)
You can also add fields to data types that already exist:
Prompt: "Add Location and Hiring Manager fields to my Job data type"
IMAGE TK
You can view and edit any generated data types in the data tab immediately.
Limitations:
The Agent cannot delete data types or field types, or remove fields from existing data types – we want this to remain an explicit user action for now
The Agent cannot modify exiting field types (like converting a Salary field to be a number instead of text)
The Agent cannot create or edit option sets
App-specific explanations
The AI Agent understands your app’s structure and elements, along with general context — such as the page you’re viewing or the element you’ve selected — allowing it to:
Help troubleshoot workflows and dynamic expressions
Answer questions about how elements are configured
Explain how your app is wired together
Selecting an element gives the Agent clear instructions to focus on it in relation to your prompt. The Agent also includes deep-links to UI elements in its explanations, so you can click and see what elements it’s referring to.
Context limitations
Currently, the AI Agent can’t access or interpret plugins, logs, the issue checker, or other app details beyond your app’s design, logic, and data.
Education and guidance
Bubble’s AI Agent is trained on Bubble knowledge and documentation, allowing it to guide you accurately through building, editing, or troubleshooting your app.
When you ask a question, the Agent references official sources — including the Bubble Manual — and responds with citations and helpful links. It can also search the web to surface the most relevant and up-to-date information.
This means its responses are based on trusted Bubble resources, and it can still guide you through solutions, even for tasks it can’t perform directly.
General prompting advice
Keep prompts short and focused — concise requests are easier for the AI to interpret.
Include specific details such as element names, field types, or labels.
Make one request at a time for the most accurate results.
Use Bubble terminology to describe what to create or edit.
When modifying something, specify both what should change and how.
You can also ask the AI to explain what a change will do before applying it.
What’s coming soon
The AI Agent is currently in beta and continues to evolve. Upcoming capabilities include:
Automatically generating and editing workflows
Full editing support for the native mobile editor (currently guidance only)
Improved accuracy and fewer mistakes over time
Last updated
Was this helpful?