Bubble AI Agent

The Bubble AI Agent is an in-editor assistant that helps you build, troubleshoot, and understand your app more efficiently. It uses Bubble documentation and app context to provide hands-on guidance so you can spend less time searching for answers and more time building.

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.

You can talk to the Agent the same way you’d talk to a knowledgeable colleague working alongside you in your app. Describe what you want to build, ask a question about how something works, or point to a specific problem you’re trying to solve.

The Agent understands the structure of your app: pages, views, workflows, data types, and privacy rules. That means you can reference things directly by name, and the Agent will pick them up in context. For example, you can say add a field called “priority” to the Task data type, and the Agent knows exactly which data type you’re referring to.

You can also point the Agent at what’s already in the editor. If a specific element is selected, the Agent uses that as context. If a workflow is open, it can suggest changes to that workflow. This makes it easy to work iteratively: select something, prompt the Agent, review the result, and continue.

Prompts don’t need to follow a specific format. You can:

The Agent responds to natural language, so the way you’d naturally describe the task in a conversation is usually the way to prompt it. If you’re specific about what you want, you’ll get more focused results. If you leave things open-ended, the Agent will make a suggestion and give you a chance to refine it.

You can point the Agent toward specific components, like an element or a workflow, before sending your prompt:

Click the AI Agent icon to open up a chat window.

Click the element, workflow, or other component to give the Agent additional context. Once selected, it appears as a small tag beneath the prompt input. You can select multiple components to provide more context.

The AI Agent will use the selected component as context as it interprets your prompt.
​

You can remove the mention by clicking the X on the right side of the tag.

You can prompt the Agent by speaking instead of typing. Click the microphone in the chat prompt field and start talking.

Your words appear in the prompt field in near real-time as editable text.

The first time you use voice input, your browser asks for microphone permission. Voice input stays unavailable until you allow it. You can always type your prompt instead.

The Agent supports multiple chats. When working on a specific task, like a particular workflow, page, or feature, it can help to keep that work in a single chat so the Agent has the full context of what’s been discussed and built.

When you want the Agent to work with a fresh context, you can start a new chat by clicking the + symbol in the upper right corner of the chat window.

To browse existing chats and return to a previous one, click the icon in the upper right corner of the chat window.

The Agent has the same permissions as the user who initiates the chat. If you are an editor, it can make edits on your behalf. If you only view-only permissions, the Agent will only be able to inspect and provide guidance.

If you have collaborators in your app, their Agent will inherit their permissions. This ensures that someone with read-only or view-only permissions to your app will not be able to edit your app using the Agent. If they try to edit, the Agent will gracefully decline.

You can control the AI Agent’s access to the database under Settings – Collaboration – Agent permissions. See this section for more info.

The AI Agent can build an entire app from scratch, from just one prompt. Instead of starting from a blank canvas, you can describe what you want your app to do the the AI Agent, and it will set up a plan and execute with your approval.

The finished product comes complete with pages, elements, a database, workflows and sample data for your development environment. In addition to the features you specifically ask for, the Agent will also build out typical needed core features like sign-up, login and reset password flows.

This allows you to get started instantly, reducing the time it takes to go from idea to working prototype. By seeing the app in the editor, and asking the AI Agent questions, you’ll also quickly learn how Bubble’s logic works.

Article:Generate apps with AI

The AI Agent also helps you continue developing your app after the first version is done. It can add and edit pages, wire up workflows, structure your database, connect to external APIs, make style changes and many other things.

Additionally, the Agent can explain how your app works, read data and offer guidance as you keep building. The combination of the know-it-all Agent and Bubble’s easy-to-use visual editor makes powerful app development approachable, whether you’re building your first app or your fiftieth.

Article:Edit apps with AI