Technical Onboarding Guide

Get Started with
Claude Code at FedEx

Complete step-by-step setup instructions for deploying Claude Code across your engineering teams. Choose from three deployment options based on your infrastructure and security requirements.

Choose Your Deployment Path

Select the integration option that best fits FedEx's infrastructure

🚀

Direct Access

  • Setup Time: 30 minutes
  • Best For: Pilot programs, small teams
  • Requirements: Internet access, API key
  • Tools: CLI, VS Code extension
🔷

Google Vertex AI

  • Setup Time: 2-4 hours
  • Best For: GCP-native deployments
  • Requirements: GCP project, IAM
  • Tools: Vertex API, Cloud Logging

Option 1: Direct Access Setup

1 Prerequisites Check

Ensure you have the following before starting:

2 Install Claude Code CLI

Install the Claude Code command-line tool:

macOS / Linux:

# Install via npm npm install -g @anthropic-ai/claude-code # Or via curl curl -fsSL https://claude.ai/install.sh | sh # Verify installation claude-code --version

Windows (PowerShell):

# Install via npm npm install -g @anthropic-ai/claude-code # Verify installation claude-code --version

3 Configure API Key

Set up your Anthropic API key as an environment variable:

# Add to ~/.bashrc, ~/.zshrc, or ~/.bash_profile export ANTHROPIC_API_KEY="sk-ant-your-api-key-here" # Or configure via CLI claude-code config set api-key sk-ant-your-api-key-here # Verify configuration claude-code config get api-key
⚠️ Security Best Practice: Never commit API keys to version control. Use environment variables or secure credential managers like HashiCorp Vault or GCP Secret Manager.

4 First Project Setup

Initialize Claude Code in your FedEx project:

# Navigate to your project cd ~/fedex-projects/shipping-api # Initialize Claude Code claude-code init # This creates .claude/ directory with project settings # Configure which files/folders to analyze: claude-code config set include "src/**/*.java,src/**/*.py" claude-code config set exclude "node_modules,build,dist"
💡 Tip: Claude Code automatically respects .gitignore patterns and won't analyze excluded files.

5 Try Your First Command

Test Claude Code with a simple query:

# Ask Claude to analyze your codebase claude-code "Find all database queries that could cause N+1 problems" # Generate tests for a specific class claude-code "Write unit tests for ShippingCalculator.java" # Refactor code claude-code "Refactor the authentication module to use JWT tokens" # Explain code claude-code "Explain what the TrackingService class does"

6 Install VS Code Extension (Optional)

For IDE integration, install the Claude Code VS Code extension:

  1. Open VS Code
  2. Go to Extensions (⇧⌘X or Ctrl+Shift+X)
  3. Search for "Claude Code"
  4. Click Install
  5. Reload VS Code
💡 Features: Inline code suggestions, chat panel, automatic code reviews, and refactoring tools directly in your editor.

Option 3: Google Vertex AI Setup

1 GCP Prerequisites

2 Enable Vertex AI API

# Enable Vertex AI API gcloud services enable aiplatform.googleapis.com # Set default project and region gcloud config set project fedex-ai-project gcloud config set ai/region us-central1 # Verify access gcloud ai models list --region=us-central1

3 Install Google Cloud SDK and Anthropic SDK

Python:

pip install google-cloud-aiplatform anthropic

Node.js:

npm install @google-cloud/aiplatform @anthropic-ai/sdk

4 Configure Vertex AI Connection

Python Example:

from anthropic import AnthropicVertex # Initialize Vertex AI client client = AnthropicVertex( project_id="fedex-ai-project", region="us-central1" ) # Use Claude via Vertex AI response = client.messages.create( model="claude-sonnet-4-5@20250101", max_tokens=4096, messages=[ {"role": "user", "content": "Analyze this code..."} ] ) print(response.content)

Node.js Example:

import { AnthropicVertex } from '@anthropic-ai/vertex-sdk'; // Initialize Vertex AI client const client = new AnthropicVertex({ projectId: 'fedex-ai-project', region: 'us-central1' }); // Use Claude via Vertex AI const response = await client.messages.create({ model: 'claude-sonnet-4-5@20250101', max_tokens: 4096, messages: [ { role: 'user', content: 'Analyze this code...' } ] }); console.log(response.content);

5 Service Account Configuration

Create a service account for production deployments:

# Create service account gcloud iam service-accounts create claude-code-sa \ --display-name="Claude Code Service Account" # Grant Vertex AI permissions gcloud projects add-iam-policy-binding fedex-ai-project \ --member="serviceAccount:claude-code-sa@fedex-ai-project.iam.gserviceaccount.com" \ --role="roles/aiplatform.user" # Download service account key gcloud iam service-accounts keys create claude-key.json \ --iam-account=claude-code-sa@fedex-ai-project.iam.gserviceaccount.com # Set environment variable export GOOGLE_APPLICATION_CREDENTIALS="./claude-key.json"

6 Monitoring with Cloud Logging

Query usage and performance metrics:

# View logs gcloud logging read "resource.type=aiplatform.googleapis.com/Endpoint" \ --limit=50 \ --format=json # Query metrics gcloud monitoring time-series list \ --filter='metric.type="aiplatform.googleapis.com/prediction/online/response_count"' \ --format="table(metric.labels.model_version)"

Next Steps

📚

Read Documentation

Explore the complete Claude Code API reference, best practices, and advanced features.

View Docs →
🎓

Join Training Sessions

Schedule live training sessions for your FedEx engineering teams with Anthropic experts.

Schedule Training →
💬

Get Support

Access dedicated support channels, Slack workspace, and technical account management.

Get Support →

Need Help Getting Started?

Our team is here to support your deployment. Schedule a technical onboarding session with Anthropic engineers.

Schedule Onboarding Session