Maia Make Capabilities
Introduction
Maia Make capabilities are available in Studio Pro 11.8 and above.
To use Maia Make capabilities, you need an internet connection. You must be signed in to Studio Pro unless you have configured a bring your own agent (BYO Agent).
Maia Make is a set of AI-assisted development capabilities in Studio Pro that are available through a unified conversational interface. Describe your requirements in natural language, and Maia generates development artifacts such as data structures, pages, and microflows.
You can also ask Maia to provide explanations of your existing documents, such as microflows, workflows, and pages. Moreover, this interface allows you to integrate with external tools, such as Playwright and Figma, via MCP servers. It also supports story-based development by generating app artifacts based on existing user stories.
For guidance on how to best prompt Maia, refer to Prompt Engineering.
Maia Make Capabilities Overview
Supported Document Types
Maia Make can generate new documents, modify existing documents, and explain app documents and structures through a unified conversational interface. The following table lists all document types that Maia Make can work with and the Studio Pro version in which support for each document type was introduced:
| Document Type | Available in Maia Make from | Remarks |
|---|---|---|
| Domain model | Studio Pro 11.8 | |
| Pages | Studio Pro 11.8 | |
| Microflows | Studio Pro 11.8 | In Studio Pro 11.9 and above, Maia can delete flows and microflow objects, but cannot change activity types or replace complex configuration settings. In Studio Pro 11.8, Maia can change variable names, move objects, and reconnect flows for existing objects, but cannot delete objects or flows or change activity types. |
| Workflows | Studio Pro 11.9 | |
| OQL | Studio Pro 11.9 | |
| View entities | Studio Pro 11.9 | |
| Enumerations | Studio Pro 11.9 | |
| Constants | Studio Pro 11.9 | |
| Modules | Studio Pro 11.9 | |
| Java actions | Studio Pro 11.9 | Read-only; Java actions cannot be generated. |
| JavaScript actions | Studio Pro 11.9 | Explain-only in Studio Pro 11.9. Generation, adding parameters, and updating the associated JavaScript file available from Studio Pro 11.10. |
| Navigation | Studio Pro 11.11 | |
| Menu | Studio Pro 11.11 | |
| Data Transformers | Studio Pro 11.12 | |
| JSON Structures | Studio Pro 11.13 | |
| Change Data Capture | Studio Pro 11.14 | |
| Task Queues | Studio Pro 11.15 |
Maia Make Standalone Capabilities
The following table lists Maia Make Standalone Capabilities and the Studio Pro version in which each capability was introduced:
| Capability | Description | Available in Maia Make from | Remarks |
|---|---|---|---|
| Maia Chat | Answers questions about all aspects of Mendix development. | Studio Pro 11.8 | |
| Maia Explain | Explains the purpose and logic of existing documents. | Studio Pro 11.8 | Can be used directly in the chat interface, or in the App Explorer by right-clicking a document and clicking Maia Explain. |
| Maia MCP Client | Connects Maia to external MCP servers, giving it access to third-party tools. | Studio Pro 11.8 | |
| Studio Pro MCP Server | Exposes Studio Pro as an MCP server for use by external AI tools. | Studio Pro 11.10 | |
| Maia Web Fetch | Fetches and reads content from public websites and APIs. | Studio Pro 11.10 | |
| Maia Agent Skills (SKILLS.md) | Extends Maia with reusable knowledge. | Studio Pro 11.11 | Maia can create and edit skills directly in chat, for both project-level and module-level skills, from Studio Pro 11.15. |
| Maia Agent Instructions (AGENTS.md) | Extends Maia with instructions to be followed with every prompt | Studio Pro 11.12 |
Maia Make General Capabilities
The following table lists the general capabilities of Maia Make and the Studio Pro version in which support for each capability was introduced:
| Capability | Description | Available in Maia Make from | Remarks |
|---|---|---|---|
| Story-based development | Generates app artifacts based on existing user stories to support story-driven development workflows. | Studio Pro 11.8 | |
| PDF/image support | Allows you to provide PDFs and images as input to help Maia better understand your requirements. | Studio Pro 11.8 | |
| Adding documents as context | Lets you add relevant documents to provide Maia with additional context. | Studio Pro 11.8 | |
| Editing existing documents | Enables Maia to modify existing documents, including renaming elements. | Studio Pro 11.8 | |
| Removing elements | Allows Maia to remove elements from documents to support more advanced refactoring tasks. | Studio Pro 11.9 | |
| Undo support | Allows you to undo Maia-generated changes on a per-document basis. | Studio Pro 11.9 | |
| Folder structure support | Organizes new documents into existing folders and follows your established folder hierarchy when generating content. | Studio Pro 11.10 | Not supported for pages. |
| Themes and styling | Allows Maia to modify theme variables, create custom styling, and manage design properties. | Studio Pro 11.12 | |
| Markdown attachment support | Allows you to provide Markdown documents as input to help Maia better understand your requirements. | Studio Pro 11.12 | |
| Explain and solve consistency errors | Allows you to use Maia to explain or solve problems by right-clicking the item in the Errors pane. | Studio Pro 11.12.1 |
Using Maia Make Capabilities
Maia Make capabilities are enabled by default. You can disable them in Studio Pro Preferences, via the Maia tab.
To access the conversational interface and Maia Make capabilities, in the upper-right corner of Studio Pro, click the Maia pane. It appears under the Chat tab:
Alternatively, you can click View on the Studio Pro top bar and select Maia to open the interface.
In Studio Pro 11.7 and below, the Chat tab is only used for Maia Chat where you can ask questions about all aspects of Mendix.
There is also the Learn tab under the Maia pane. It is a separate Maia capability that is not part of Maia Make capabilities. For more information, see Maia Learn.
Maia Make Capabilities Interface Overview
The conversational interface includes the following features.
New Chat
Clicking New Chat allows you to clear the messages and start a new conversation that does not reference your current chat.
Configure MCP Connections
This option ( ) allows you to connect external MCP servers to Maia, giving it access to third-party tools during chat. For more information on how to configure MCP connections, see Maia MCP Client.
Add
Add allows you to attach images, PDFs, or user stories to help Maia understand your requirements better.
Add file to Maia Chat
This option (@ icon) allows you to add certain logic or pages to Maia as context. You can also access this option by right-clicking the documents (microflows or pages) in the App Explorer, where it appears in the context menu.
Changed List
A list of items added or changed by Maia appears above the chat box. Click an entry to open the relevant document. To undo all changes, click Undo all. To undo a single change, click the undo button on the right side of that item.
Clarifying Questions
When Maia needs more information, it asks clarifying questions through a dedicated UI to improve the quality of its response.
Save a Maia Session
A Maia session contains your conversation history and context, which can help analyze Maia's responses and behavior for troubleshooting or support purposes. To save a Maia session, go to Help > Support Tools > Capture Maia Agent Session.
In Studio Pro 11.9 - 11.11, this option is found at Help > Support Tools > Dump Maia Agent Session.
Configuring a Custom AI Provider
By default, Maia uses the Mendix platform's AI service. You can configure Maia to use your own LLM provider instead (also known as bring your own LLM or BYO LLM).
To enable custom LLM provider configuration, follow these steps:
- Open the Studio Pro settings.
- In the Preferences dialog box that opens, go to the New Features tab.
- Select the Enable configuring a custom AI provider for Maia checkbox, then click OK.
After enabling this feature, a Settings ( ) icon appears in the upper-right corner of the Maia pane.
Provider Configuration
Custom AI provider settings are per-project and local to your workstation. Each app can have its own configuration, and settings are not committed to version control.
Mendix Platform
The Mendix platform AI service is the default, recommended option and requires no configuration. Some Mendix platform optimizations may not be available if you use a custom LLM provider instead.
Amazon Bedrock
To configure Amazon Bedrock as your LLM provider, follow these steps:
- Click Settings ( ) in the Maia pane.
- Select Amazon Bedrock from the LLM Provider list.
- Create an API key in AWS, then enter the Base URL and your API Key. Studio Pro stores the API key securely across sessions.
- Enter the Model ID. You can find available model IDs in your AWS Bedrock console. Mendix recommends Claude Sonnet 4.6 for optimal Maia performance.
- Click Save Config.
OpenAI Compatible
To configure an OpenAI-compatible provider, follow these steps:
- Click Settings ( ) in the Maia pane.
- Select OpenAI Compatible from the LLM Provider list.
- Enter the Base URL for your API endpoint.
- Enter the Model ID.
- Optional: Enter your API Key. Studio Pro stores this key securely across sessions.
- Click Save Config.
LLM Gateway Configuration for Private Mendix Platform
Private Mendix Platform provides an environment where you can develop and deploy your applications within your own enterprise security boundary to ensure the highest levels of data security and compliance. Because Private Mendix Platform instances are hosted within the enterprise firewall, selecting an LLM provider other than the default Mendix Platform requires you to also configure the LLM Gateway URL.
The LLM Gateway URL is configured during the installation or upgrade of Private Mendix Platform. For more information, see Installing Maia for Private Mendix Platform.
Best Practices
Text Input
To achieve optimal results, provide context about your app or the document you are working on by describing its main use cases, customer needs, or other relevant details. The more Maia knows about what you are building, the more tailored and accurate the generated results will be.
Providing Context
Below are some examples of prompts you can use as a starting point:
- The app will help users...
- This module handles...
- Customers need to be able to...
- The page will be used to...
- Generate a workflow for a process that...
- This feature allows users to...
Editing and Improving
Below are examples of prompts you can use to ask Maia to make further edits or request explanations and suggestions for improving a document:
- Can you explain the function and purpose of this document?
- I want an area on the page where users can...
- Remove the ... widget.
- How can I make this page more user-friendly or visually appealing?
- Could you identify any potential issues with this document and recommend solutions?
- Can you give me suggestions to improve this workflow?
Image Input
The image size is limited to 512 KB. Make sure to select a clear image to help Maia better understand your request. For example, you can provide a screenshot, a photo, a design mock-up, or a close-up picture of a drawing. Avoid heavily compressed or low-quality images, as these may result in the loss of important details.
Keep in mind that Maia analyzes only the structure of the image. Maia does not change the theming of your app, such as the color scheme. This can cause some differences between the provided image and the generated page.
Microflows
When generating microflows, consider the following additional guidelines:
- Be specific: Clearly describe the desired outcome and the steps involved. For example, instead of using Create a user, use Create a new user object, set its name attribute to 'John Doe', and commit it.
- Use keywords: Incorporate terms relevant to microflow activities, such as create object, retrieve, change object, show message, loop, or decision. This can help with correct microflow generation.
- Provide context: If your microflow interacts with existing entities or attributes, mention them in your text input.
Workflows
You can provide a BPMN image representing employee onboarding alongside your text input. Maia can analyze the image, rework it using Mendix Workflows terminology, and generate the corresponding activities. Use text input alongside the image to specify any differences. For example, "Generate a workflow based on this BPMN image, but make sure it waits before sending an email to the new employee."