---
title: "Rowboat Studio"
description: "Visual interface to build, test, and deploy multi-agent AI assistants using plain language"
icon: "puzzle-piece"
---


## Overview

**Rowboat Studio** is your visual interface for building AI assistants — powered by agents, tools, and workflows — using plain language and minimal setup. It brings the process of creating multi-agent systems down to just a few clicks.

Workflows created within Rowboat are known as **assistants**, and each assistant is composed of:
- One or more **agents**
- Attached **tools** and **MCP servers**

Once built, assistants can be tested live in the **playground** and deployed in real-world products using the [API](/docs/api-sdk/using_the_api) or [SDK](/docs/api-sdk//using_the_sdk).

---

## Key Components

Here’s what you’ll interact with in Studio:

| Component  | Description | Highlights |
|------------|-------------|------------|
| **Agent**     | Core building blocks of your assistant.<br />Each agent handles a specific part of the conversation and performs tasks using tools and instructions. | • Define behavior in plain language<br />• Connect agents into a graph<br />• Attach tools and RAG sources |
| **Playground** | Interactive testbed for conversations.<br />Lets you simulate end-user chats with your assistant and inspect agent behavior in real time. | • Real-time feedback and debugging<br />• See tool calls and agent handoffs<br />• Test individual agents or the whole system |
| **Copilot**    | Your AI assistant for building assistants.<br />Copilot creates and updates agents, tools, and instructions based on your plain-English prompts. | • Understands full system context<br />• Improves agents based on playground chat<br />• Builds workflows intelligently and fast |

> **Agents are the heart of every assistant.** Learn more about how they work in the Agents page.

<Card title="Agents" icon="robot" horizontal href="/docs/using-rowboat/agents">
  Learn about creating and configuring individual agents within your multi-agent system
</Card>
---

## Building in Rowboat

<Steps>
  <Step title="Describe your assistant to Copilot">
    Use plain language to tell Copilot what you want your assistant to do. Copilot will auto-generate the agents, instructions, and tools that form the base of your assistant.
  </Step>

  <Step title="Review and apply Copilot suggestions">
    Inspect the created agents — especially their instructions and examples — and refine or approve them before moving forward.
  </Step>

  <Step title="Connect MCP servers and tools">
    Integrate external services, tools, and backend logic into your agents using Rowboat's modular system. Tools are tied to agents and triggered through instructions.
  </Step>

  <Step title="Test in the Playground">
    Use the chat playground to simulate real-world conversations. You’ll see which agent takes control, what tools are triggered, and how your assistant flows.
  </Step>

  <Step title="Deploy via API or SDK">
    Assistants can be deployed into production using the **Rowboat Chat API** or the **Rowboat Chat SDK**. Both support stateless and stateful conversation flows.
  </Step>
</Steps>