Claude Code on Amazon Bedrock: Quick Setup Guide

What is Claude Code?

• Edits files and fixes bugs across your codebase
• Answers questions about code architecture and logic
• Executes and fixes tests, resolves merge conflicts, and more
• Works directly from your terminal with your local environment

Claude Code Models

• Claude 3.7 Sonnet: The primary model that handles complex code understanding, generation, and reasoning tasks
• Claude 3.5 Haiku: A lightweight model used for specific functions within Claude Code:
  • Faster response times for simpler queries
  • More efficient token usage for routine operations
  • Handling background tasks and file indexing
  • Preprocessing and filtering code before sending to the more powerful Sonnet model

⚠️ IMPORTANT ⚠️: You must explicitly enable access to both Claude 3.7 Sonnet and Claude 3.5 Haiku models in your AWS Bedrock Model Access settings for the region you're using. Failure to enable either model will result in 403 Forbidden errors when using Claude Code. 🔑 🚫

See the AWS Bedrock Getting Started Guide for instructions on enabling model access.

About Claude 3.7 Sonnet

• Superior code comprehension and generation capabilities
• Enhanced reasoning for debugging complex issues
• Improved context handling for navigating large codebases
• Better understanding of programming concepts and patterns
• Optimized for terminal-based interactions in Claude Code

Benefits of Using Claude Code with Amazon Bedrock

• Leverage your existing AWS Bedrock allocation and billing
• Access to Claude 3.7 Sonnet's advanced coding capabilities
• Keep your code interactions within your AWS infrastructure
• Potentially access higher rate limits when properly configured
• Maintain consistent security and compliance standards
• Use prompt caching (if available) for cost optimization

Before you begin

Check system requirements

• Operating Systems: macOS 10.15+, Ubuntu 20.04+/Debian 10+, or Windows via WSL
• Hardware: 4GB RAM minimum
• Software:
  • Node.js 18+
  • git 2.23+ (optional)
  • GitHub or GitLab CLI for PR workflows (optional)
  • ripgrep (rg) for enhanced file search (optional)
• Network: Internet connection required for authentication and AI processing

AWS Credentials Setup

Quick AWS Credential Setup:

1. Using AWS CLI (easiest method):
   • Run aws configure
   • Enter your access key, secret key, default region (ensure you have Bedrock access in that region), and set output to json.
2. Manual Configuration:
   • Create credential files in ~/.aws/credentials and ~/.aws/config

Setting up Claude Code with Amazon Bedrock

Important: Prompt Caching & Cost Management

About Prompt Caching:

• What it does: Significantly reduces token usage and costs by caching prompts
• Availability: Available to select Bedrock customers in preview (coming to Bedrock GA in the future)
• How to control: Use the DISABLE_PROMPT_CACHING environment variable:
  • Set to 1 to disable caching
  • Omit this variable or set to 0 to enable caching (if you have access)

Recommendations:

• If you have access to prompt caching (preview or GA): Definitely use it! Just omit the DISABLE_PROMPT_CACHING variable or set it to 0.
• If you don't have prompt caching: Be mindful of usage as costs can accumulate quickly.
  • Monitor your usage with the /cost command within Claude Code
  • Consider using /compact and /clear commands regularly to manage context size

Project Initialization with /init

What /init Does:

• Generates a comprehensive CLAUDE.md guide for your project
• Creates documentation tailored to your specific codebase
• Helps new team members understand the project structure
• Provides a reference for working with Claude Code in your project

How to Use /init:

1. Start Claude Code in your project directory with claude
2. Type /init in the interactive REPL
3. Claude will analyze your codebase and generate the guide
4. Review the generated CLAUDE.md file
5. Optionally commit the file to your repository with claude commit

Accepting and Reviewing Code Additions from Claude Code

Permission System

• Claude Code uses a human in the loop permission system for safety
• File modifications require explicit approval by default
• You'll be prompted to confirm before changes are made

Best Practices for Code Review

1. Carefully examine suggested changes before approving them
2. Understand what the code does - ask Claude to explain if needed
3. Check for edge cases that might not have been considered
4. Verify security implications of any code that handles sensitive data
5. Test the changes after they're applied to ensure they work as expected

⚠️ IMPORTANT ⚠️: You should always use the Yes option and avoid using "Yes, don't ask again" to ensure that all code, file changes, and commands generated by Claude are strictly reviewed by a human. This human-in-the-loop review process is critical for maintaining security and code quality. 👁️ 🔒

Managing Context with the /compact Command

• What it does: Summarizes your conversation history into a concise format
• Benefits: Preserves essential information while reducing token count
• When to use: After completing major tasks, when responses slow down, or before starting new subtasks
• Token savings: Significantly reduces token usage, helping manage costs even with prompt caching

Monitoring Your Costs with Claude Code

• During a session: Use the /cost command to see current token usage and estimated costs
• Session summary: View a cost summary automatically displayed when exiting Claude Code
• Set spend limits: Configure spending thresholds through your account settings

Next Steps

Additional Resources and Continued Learning

Building a Calculator Web App with Claude Code: A Step-by-Step Tutorial

• Build a complete calculator web application from scratch
• Demonstrate Claude Code's capabilities for code generation and enhancement
• Show how to add scientific calculator functions to an existing project
• Explore best practices for working with AI coding assistants
• Provide practical examples of context management with /compact