MaiAgent Build Overview

MaiAgent Build is a platform for building your organization's own AI assistants: define roles, knowledge, tools, and permissions, connect databases and enterprise systems, test before launch, and moni

Turn your ideas into enterprise-grade Agents.

MaiAgent Build lets IT staff and technical partners build their organization's own AI assistants: define roles, knowledge, tools, and permissions, and connect databases and enterprise systems so AI assistants can retrieve data, call systems, and follow workflows to get things done. The AI assistants used in MaiAgent Work and MaiAgent Serve are also built and managed here.

Products

Agent Builder

Define role instructions, knowledge bases, databases, tools, skills, and Agent Teams in one place, and configure an AI assistant ready for deployment.

AI Gateway

Connect your organization's own model providers or self-hosted models, manage the model catalog and fallback model groups, and monitor traffic and anomalies.

AgentOps and Governance

Test datasets, automated evaluations, AI assistant monitoring, and tool execution records; Hook checks personal data and content as messages enter and leave the AI.

Developer Tools

View API call logs, or use MaiAgent MCP to let external AI tools such as Claude and Cursor operate the platform directly.

Agent Builder Modules

Module	Enables AI assistants to…
AI Assistants	Understand requests and generate responses based on role instructions; configure Agent Schedules to run tasks at set times
Knowledge Bases	Answer questions using enterprise documents, FAQs, and web content
Databases	Query structured data using natural language (Text to SQL)
Tools	Call external systems and perform actions through MCP or APIs
Skills	Follow a set of multistep procedures (SOPs) to complete tasks
Code Interpreter, Browser Tool	Run code to process files, or operate a browser to complete web workflows
Agent Teams	Collaborate across multiple AI assistants with different specialties
Hook Message Interception	Automatically mask personal data or intercept content before it enters the AI or before a response is sent

Not sure which module to use? See I want to do X. What should I use?.

Build Workflow

1

Create an AI Assistant

Create an AI assistant and write its role instructions; you can also apply an official template from the Agent Template Library and customize it.

2

Connect Knowledge and Capabilities

Attach a knowledge base, then add databases, tools, and skills when the assistant needs to retrieve data or perform actions.

3

Test Before Launch

Use test datasets and automated evaluations to verify response quality, then launch for external users through MaiAgent Serve channels, or make the assistant available to employees in MaiAgent Work.

4

Monitor Continuously After Launch

In AgentOps, review response quality and tool execution records, and add conversations with poor answers to the FAQ to keep improving.

Permissions and Governance

Assign access permissions for AI assistants, knowledge bases, and conversation platforms by role. Organization owners can also restrict which models members and AI assistants can call. See Role-Based Resource Access, Model Access Permissions, and Third-Party Login (SSO). Use the Activity Log to look up and export who changed which settings and when.

Further Integration

To integrate MaiAgent programmatically, see the technical guide and API documentation:

• API Quickstart

• AI Gateway: OpenAI-Compatible API Integration

• Self-Hosted MCP Server Integration Specifications

• API Documentation

Use Cases

• External Data Integration: Connect external API data to AI assistants

• AI Assistant Optimization Consultant: Automatically diagnose response quality and suggest adjustments to role instructions and knowledge bases