SETTING UP CLAUDE

Option A: Web Interface (claude.ai)

Step 1: Navigate to claude.ai

Step 2: Click "Sign Up"

Step 3: Choose signup method (Google, Email, or Apple ID)

Step 4: Verify your email

Step 5: Complete phone verification (anti-abuse measure)

Step 6: Select your plan (Free, Pro, Team, or Enterprise)

Step 7: Complete payment if applicable

Step 8: Start chatting!

Plan Comparison:

Recommendations:

• Free Plan: Experimentation, learning, low-volume personal use
• Pro Plan ($20/mo): Daily professional use, content creation, research (minimum for serious work)
• Team Plan: Small teams, shared context, collaborative prompting
• Enterprise: Production deployments, compliance requirements, high volume

Step 1: Generate API Key

1. Login to console.anthropic.com
2. Navigate to API Keys section
3. Click "Create Key"
4. Name it (e.g., "Development Key" or "Production Key")
5. Set permissions (Read/Write or restrict as needed)
6. COPY THE KEY IMMEDIATELY - it's only shown once!

Step 2: Store Your Key Securely

DO NOT hardcode keys in your code.

DO NOT commit keys to git.

Correct way - Environment Variable (macOS/Linux):

# Add to your ~/.bashrc, ~/.zshrc, or ~/.profile
export ANTHROPIC_API_KEY="sk-ant-api03-your-key-here"

# Then reload
source ~/.bashrc

Correct way - .env file (for projects):

# Create .env file (never commit to git!)
echo "ANTHROPIC_API_KEY=sk-ant-api03-your-key-here" > .env
echo ".env" >> .gitignore

Correct way - Production (Secrets Manager):

# AWS Secrets Manager or similar
import boto3
from anthropic import Anthropic

client = boto3.client('secretsmanager')
secret = client.get_secret_value(SecretId='anthropic/api-key')
api_key = secret['SecretString']

claude = Anthropic(api_key=api_key)

Step 3: Verify Your Key Works

curl <https://api.anthropic.com/v1/messages> \\
  -H "x-api-key: $ANTHROPIC_API_KEY" \\
  -H "anthropic-version: 2023-06-01" \\
  -H "content-type: application/json" \\
  -d '{
    "model": "claude-3-haiku-20240307",
    "max_tokens": 10,
    "messages": [{"role": "user", "content": "Say OK"}]
  }'

Expected response: A JSON object with Claude's response.

Installation:

Python:

bash

pip install anthropic

JavaScript/TypeScript:

bash

npm install @anthropic-ai/sdk

Go:

bash

go get github.com/anthropics/anthropic-sdk-go

Your First API Call (Python):

Create a file called first_claude.py:

python

import anthropic
import os

# Initialize the client
client = anthropic.Anthropic(
    api_key=os.environ.get("ANTHROPIC_API_KEY")
)

# Make your first API call
response = client.messages.create(
    model="claude-3-haiku-20240307",  # Start with Haiku (cheap and fast)
    max_tokens=100,                   # Limit response length
    messages=[
        {"role": "user", "content": "Write a haiku about programming"}
    ]
)

# Print the response
print(response.content[0].text)

Run it:

bash

python first_claude.py

Expected output (something like):

text

Lines of code flow,
Bugs hide in shadows deep,
Debugging takes time.

Try Different Models:

python

# Haiku (fast, cheap)
response = client.messages.create(
    model="claude-3-haiku-20240307",
    ...
)

# Sonnet (balanced - use this most of the time)
response = client.messages.create(
    model="claude-3-sonnet-20241022",
    ...
)

# Opus (most capable, slower, expensive)
response = client.messages.create(
    model="claude-3-opus-20240229",
    ...
)

Hands-On Challenge:

Modify the code to ask Claude: "Explain the difference between Haiku, Sonnet, and Opus like I'm choosing a superhero team."

Run it with all three models. Compare the responses.