---
title: "Multi-Tool Reasoning Code"
source: https://docs.autohand.ai/agent-sdk/tutorials/200-multi-tool-reasoning
---

# Multi-Tool Reasoning

Learn how to build coding assistants that use multiple tools across turns with the Autohand Code Agent SDK. Available in TypeScript, Python, and Java.

In this tutorial, you'll build a coding assistant that uses multiple tools across different turns to understand code, run tests, and report a summary. This demonstrates the ReAct loop with multi-tool turns.

**Prerequisites:**

-   Completed [Code Reviewer Agent](100-code-reviewer-agent.html)
-   Node.js 16+ (for TypeScript), Python 3.10+ (for Python), or Java 11+ (for Java)
-   SDK installed for your chosen language
-   API key from your LLM provider (set as `AUTOHAND_API_KEY`)

## What You'll Build

A code analyst coding assistant that:

-   Uses READ\_FILE to examine source code
-   Uses BASH to run commands and tests
-   Uses GLOB to find files
-   Coordinates multiple tools across turns
-   Provides a comprehensive codebase summary

## Step 1: Direct Tool Execution

Before building the agent, let's understand direct tool execution in your chosen language:

## Step 2: Create the Multi-Tool Agent

Now create an agent that uses multiple tools across turns in your chosen language:

## Step 3: Run the Agent

Run the agent with a complex prompt that requires multiple tools in your chosen language:

## Key Concepts

1

**Tool Coordination**

The coding assistant automatically coordinates multiple tools across turns to complete complex tasks.

2

**ReAct Loop**

The ReAct (Reason + Act) loop allows the coding assistant to reason about what to do, take action, and repeat.

3

**State Management**

The coding assistant maintains context across turns, remembering what it has done and what it needs to do next.

4

**Turn Limits**

Setting `maxTurns` prevents infinite loops and controls resource usage.

## Complete Example

Here's the complete example with a sample project:

## Next Steps

### 📁 View the Example

See the complete example in the TypeScript SDK repository.

[View on GitHub →](https://github.com/autohandai/agent-sdk-typescript/tree/main/examples/10-multi-tool-reasoning)

### 🔧 Sequential Agent Pipeline

Learn how to chain multiple agents together for complex workflows.

[View Example →](https://github.com/autohandai/agent-sdk-typescript/tree/main/examples/22-sequential-agent-pipeline)

### 📚 Code Modernization

Advance to code modernization and real-world applications.

[Next Tutorial →](400-code-modernization.html)