> ## Documentation Index
> Fetch the complete documentation index at: https://docs.maia.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Maia product overview

> An introduction to Maia and its three core components: Maia Foundation, Maia AI Agents, and the Context Engine.

export const mission_control = "Mission Control";

export const context_engine = "Context Engine";

export const s_runner = "Streaming runner";

export const m_runner = "Maia runner";

export const designer = "Designer";

export const maia_agents = "Maia AI Agents";

export const foundation = "Maia Foundation";

export const maia = "Maia";

{maia} is made up of three integrated components: {foundation}, {maia_agents}, and {context_engine}. {foundation} provides the cloud-native execution infrastructure for building and running data pipelines. {maia_agents} operate within that infrastructure to build, maintain, and optimize pipelines using natural language. {context_engine} supplies the institutional knowledge that {maia_agents} reason against, so that the pipelines they produce are consistent with your data standards and business logic.

These docs use "Maia" to refer to the platform as a whole. Where it's necessary to distinguish between the three components, the full component name is used.

***

## Maia Foundation

{foundation} is the cloud-native execution layer that underpins {maia}. It provides the infrastructure for connecting to data sources, building and running pipelines, and governing data operations across your organization.

### Designer

{designer} is the visual canvas where you build and manage data pipelines in {maia}. Pipelines are composed of connected components that you configure to load, transform, and orchestrate data. {designer} uses a Git-based branching model so that multiple team members can work on pipelines simultaneously and promote changes through environments in a controlled way.

For more information, read [Using {designer}](/docs/guides/using-designer).

### Pipelines

{maia} supports three pipeline types:

* **Orchestration pipelines** define the sequence and control flow of data loading tasks, including conditional branching, iteration, and error handling.
* **Transformation pipelines** reshape and prepare data within your warehouse using drag-and-drop components, without requiring you to write SQL.
* **Test pipelines** run another pipeline and check its results, so you can verify that pipelines behave correctly before deploying them to production.

{maia_agents} can build all three pipeline types when you describe what you need in {mission_control} or the {designer} chat panel.

To learn about pipelines and the components you can use to build them, read [Building pipelines](/docs/guides/maia-pipelines) and [Components overview](/docs/guides/components-overview). For information about test pipelines specifically, read [Test pipelines](/docs/components/test-pipelines).

### Connectors

{foundation} includes over 150 connectors for loading data from sources into your cloud data platform. You can also create custom connectors to integrate any REST API that returns a JSON response.

For more information, read [Connectors overview](/docs/components/connectors-overview) and [Custom connector overview](/docs/guides/custom-connector-overview).

### Streaming

{foundation} supports near-real-time data collection through streaming pipelines. These pipelines capture and synchronize data changes from source databases and write them to a target data warehouse.

For more information, read [Streaming pipelines](/docs/streaming/streaming-pipelines/).

### Runners

A {m_runner} executes the tasks defined in your {designer} pipelines. In a Full SaaS deployment, Matillion hosts and manages the {m_runner} on your behalf. In a Hybrid SaaS deployment, you host the {m_runner} in your own cloud environment (AWS, Azure, Google Cloud, or Snowflake). A {s_runner} handles execution of streaming pipelines.

For more information, read [{m_runner} overview](/docs/guides/runner-overview).

### Deployment and security

{foundation} can be deployed as a fully Matillion-hosted SaaS solution, as a Hybrid SaaS deployment where the {m_runner} runs in your own cloud, or natively inside Snowflake. All deployment models use a pushdown architecture, meaning data is processed within your cloud data platform and does not pass through Matillion infrastructure.

{foundation} supports Single Sign-On (SSO), Multi-Factor Authentication (MFA), and Role-Based Access Control (RBAC). For compliance details, read [Cloud platform security and compliance](/docs/security/cloud-platform-security-compliance).

***

## Maia AI Agents

{maia_agents} are the agentic layer of {maia}. They operate inside the {foundation} execution environment, interacting with {designer} and your data platform directly on your behalf. You can communicate with {maia_agents} using natural language in the chat panels in {designer} and {mission_control}.

{maia_agents} can build orchestration and transformation pipelines, create custom connectors, query and explore your data warehouse, manage project files, analyze and optimize existing pipelines, and commit and push changes to Git. {context_engine} provides the knowledge base that {maia_agents} draw on during these tasks, so that the pipelines they build reflect your organization's data standards and business rules.

{maia_agents} are enabled at account level by default, meaning all users in your organization can prompt them immediately. Admins can disable {maia_agents} or restrict their ability to sample data from the account settings.

To learn more, read [{maia_agents} overview](/docs/guides/maia-ai-agents-overview).

### Mission Control

{mission_control} is the organizational center for {maia_agents}. Use it to create and manage autonomous tasks that {maia_agents} work through without requiring you to stay in the chat panel. When creating a task, you select a knowledge graph from {context_engine} to give {maia_agents} the context they need for that task.

You can also create and manage tasks programmatically using the agent tasks API. For more information, read [Mission Control](/docs/guides/mission-control) and [Using the agent tasks API](/docs/api-reference/using-agent-tasks-api).

***

## Context Engine

<Badge color="green" shape="pill" stroke size="lg">Public preview</Badge>

{context_engine} is the knowledge layer of {maia}. It stores and structures institutional knowledge—including business definitions, compliance rules, data lineage, table and column relationships, and warehouse metadata—so that {maia_agents} can reason against it when building and maintaining pipelines.

Knowledge is organized into knowledge graphs, each populated by crawlers that connect to your data warehouse and pipeline execution history on a schedule. {context_engine} also learns from your chat history with {maia_agents}; each conversation can automatically update semantic information in the knowledge graph, so the knowledge base evolves as your data landscape does.

When you create a task in {mission_control} or work with {maia_agents} in the chat panel, you can select a knowledge graph to use, giving {maia_agents} the context they need to produce results that are consistent with your data standards.

For more information, read [Context Engine](/docs/guides/context-engine).