Maia by Make system card

This system card covers Maia's functionality, data usage, human intervention points, and data security.

Maia is an AI and automation co-worker in the Scenario Builder. She helps create, modify, and debug scenarios through natural language.

Maia runs on a large language model (LLM). She interprets your natural language prompts, reasons about the current state of the scenario, and calls a set of predefined tools to modify the scenario. She autonomously chooses and orders tools in a single user-prompted session.

You interact with Maia through a conversational chat interface in the Scenario Builder. Describe what you need, for example, "add a filter that only passes emails from my domain," and Maia applies the changes step by step on the canvas while explaining its actions.

Maia relies on the following models:

Make doesn't use customer data, such as user prompts, scenario structures, or outputs, to train or fine-tune the underlying LLM. Adjustments in model behavior come exclusively from system prompt engineering and tooling configuration. No customer data modifies the model weights.

The LLM decides how to respond to each user request, including the tools to call, their order, and parameters. The output determines the scenario configuration, whose quality depends on the LLM's reasoning ability and the accuracy of its knowledge.

Maia uses these inputs in each session:

Maia processes your requests in these steps:

Maia produces the following outputs:

Maia only acts when you explicitly prompt her. While she may call multiple tools sequentially without requesting your approval for each, the outcome of these actions is visible on the canvas.

You can intervene in Maia's behavior in the following ways:

Make monitors and evaluates Maia's performance by:

By default, Maia is available in the Scenario Builder for all users. Enterprise users can opt out in their account settings.

The AI provider applies safeguards that reject prompts requesting personal data. Maia doesn't actively seek personal data. She only processes data that you explicitly include in your prompt, or that is present in the scenario you're building.

Maia never has access to your connections or keys. She uses existing capabilities in Make to connect to third-party services, and doesn’t see the data stored in them.

When credentials are required, Maia prompts you to select an existing connection or create a new one from a connection card in the chat. You enter new credentials in a dialog outside of the chat.

Never paste keys, passwords, or tokens into the chat, where Maia can see them.

Maia's availability depends on Make platform uptime and AI provider availability. Uptime targets align with Make's standard platform SLA.

Maia never indicates that you're interacting with a human agent. All of her outputs come with the following mandatory disclosure statement: "Output is generated by AI, please verify as errors may occur."

Maia's step-by-step narration of the changes she makes to the canvas provides live insight into her decision-making. More visibility into her reasoning is unavailable (a known limitation of current LLMs).

Maia's purpose is to build scenarios rather than evaluate. Her AI provider applies safety alignment frameworks to mitigate model-level biases. As the model never uses customer data for training, it does not factor in organizational biases.

Maia may produce scenarios that include bugs or logical errors, such as incorrect data transformation or unintended API calls. Mitigations include: