Anthropic Claude Integration - AgentFlow Documentation

Overview

Integrate Anthropic’s Claude models for sophisticated reasoning, analysis, and content generation. Claude excels at complex tasks requiring deep understanding and nuanced responses.

Step 1: Create the AI Connection

Get Your Anthropic API Key

Visit Anthropic Console
Sign in or create an account
Navigate to API Keys
Click Create Key
Copy and save your API key securely

Anthropic API keys are sensitive credentials. Store them securely and never expose them in client-side code.

Add Connection in AgentFlow

Go to Admin Dashboard → AI Models
Click Add Model
Fill in the basic information:
- Name: Anthropic Claude Sonnet
- Model ID: anthropic-claude
- Description: Integration with Anthropic Claude for advanced AI reasoning
Configure the API settings:
- Endpoint: https://api.anthropic.com/v1/messages
- Method: POST

Add headers:

{
  "x-api-key": "{{anthropic_api_key}}",
  "Content-Type": "application/json",
  "Anthropic-Version": "2023-06-01"
}

Configure request schema:

{
  "model": "claude-3-5-sonnet-20241022",
  "max_tokens": 4000,
  "temperature": 0.7,
  "top_p": 1,
  "top_k": 40,
  "system": "{{system_prompt}}",
  "messages": [
    {
      "role": "user",
      "content": "{{user_message}}"
    }
  ],
  "metadata": {
    "user_id": "{{user_id}}",
    "session_id": "{{session_id}}"
  }
}

Set response path: content[0].text
Click Save

Step 2: Import Configuration via YAML

Understanding YAML Structure

The YAML configuration provides a complete model setup including:

API endpoint and authentication
Request/response formatting
Message transformation rules
Custom metadata fields

YAML Configuration File

Create anthropic-claude-config.yaml:

name: "Anthropic Claude Integration"
model_id: "anthropic-claude"
description: "Integration with Anthropic Claude for advanced AI reasoning and analysis"
endpoint: "https://api.anthropic.com/v1/messages"
method: "POST"

headers:
  x-api-key: "{{anthropic_api_key}}"
  Content-Type: "application/json"
  Anthropic-Version: "2023-06-01"

request_schema:
  model: "claude-3-5-sonnet-20241022"
  max_tokens: 4000
  temperature: 0.7
  top_p: 1
  top_k: 40
  stop_sequences: []
  system: "{{system_prompt}}"
  messages:
    - role: "user"
      content: "{{user_message}}"
  metadata:
    user_id: "{{user_id}}"
    session_id: "{{session_id}}"

response_path: "content[0].text"

message_format:
  preset: "anthropic_claude"
  mapping:
    role:
      source: "role"
      target: "messages[{{message_index}}].role"
      transform: "anthropic_role"
    content:
      source: "content"
      target: "messages[{{message_index}}].content"
      transform: "none"
    timestamp:
      source: "timestamp"
      target: "metadata.timestamp"
      transform: "iso8601"
  customFields:
    - name: "claude_configuration"
      value:
        platform: "anthropic"
        model: "claude-3-5-sonnet-20241022"
        version: "2023-06-01"
        capabilities: ["reasoning", "analysis", "writing", "coding"]
      type: "object"
    - name: "generation_parameters"
      value:
        max_tokens: 4000
        temperature: 0.7
        top_p: 1
        top_k: 40
        stop_sequences: []
      type: "object"

suggestion_prompts:
  - "Analyze complex business problems and provide strategic solutions"
  - "Generate high-quality written content for various purposes"
  - "Review and improve existing code or documentation"
  - "Conduct thorough research on specific topics"
  - "Create detailed project plans and technical specifications"

Import Steps

Go to Admin Dashboard → AI Models
Click Import Model
Choose your anthropic-claude-config.yaml file
Review auto-populated settings
Enter your Anthropic API key securely
Click Import & Save

The YAML import automatically sets up message transformation and Claude-specific formatting.

Step 3: Assign to a Group

Create or Select a Group

Navigate to Admin Dashboard → Groups
Either:
- Create new group: Click New Group → Name it (e.g., “Research Team”)
- Select existing group: Click on an existing group

Assign the Model

Click Manage Models in the group settings
Find “Anthropic Claude” in the available models list
Toggle it ON
Set usage limits (optional):
- Max requests per day
- Token budget
- Priority level
Click Save Changes

Assign Claude to specialized groups for tasks requiring deep analysis and reasoning.

Step 4: Use in Chat

Starting a Claude Conversation

Go to Chat Interface
Click New Conversation
In the model selector, choose Anthropic Claude
Type your message and send!

Best Use Cases

Complex Analysis

Deep business analysis, research synthesis, strategic planning

Technical Writing

Documentation, technical specs, API references

Code Review

Thorough code analysis, security reviews, optimization suggestions

Long-form Content

Articles, reports, detailed guides, educational content

Example Interactions

Analyze our SaaS pricing strategy for a B2B platform. Current tiers: Starter ($29), Pro ($99), Enterprise (custom). Monthly users: 1,200 (60% Starter, 30% Pro, 10% Enterprise). Suggest optimizations.

Advanced Configuration

Model Variants

Claude offers different model tiers:

Model	Best For	Context Window
Claude 3.5 Sonnet	Balanced performance	200K tokens
Claude 3 Opus	Maximum capability	200K tokens
Claude 3 Haiku	Speed & efficiency	200K tokens

Parameter Tuning

Temperature (0.0 - 1.0)

temperature: 0.7  # Default - balanced
temperature: 0.2  # More focused and deterministic
temperature: 0.9  # More creative and varied

Top-K Sampling

top_k: 40   # Default - good balance
top_k: 10   # More focused selection
top_k: 100  # Broader selection

Stop Sequences

stop_sequences: ["\n\nHuman:", "END"]  # Custom stop points

System Prompts

Claude responds well to detailed system prompts:

system: |
  You are a senior technical architect with expertise in distributed systems.
  Provide detailed, technically accurate responses with code examples when relevant.
  Consider scalability, security, and maintainability in all recommendations.

Troubleshooting

Common Issues

API Key Invalid

Solution: Verify your API key in the Anthropic Console and regenerate if necessary. Ensure you’re using the correct header format: x-api-key.

Rate Limit Errors

Solution: Claude has rate limits based on your tier:

Tier 1: 50 requests/min
Tier 2: 1,000 requests/min
Tier 3: 2,000 requests/min

Implement exponential backoff or upgrade your tier.

Context Length Exceeded

Solution: Claude supports 200K tokens but responses are limited by max_tokens. Reduce conversation history or split long requests.

Response Truncated

Solution: Increase max_tokens in your configuration:

max_tokens: 8000  # For longer responses

Error Response Handling

Monitor these error types:

{
  "error": {
    "type": "invalid_request_error",
    "message": "messages: roles must alternate between 'user' and 'assistant'"
  }
}

Ensure proper message role alternation in your conversation history.

Cost Management

Token Optimization

Monitor Usage: Check Analytics Dashboard → Model Usage
Set Limits: Configure per-group token budgets
Optimize Prompts: Be concise while maintaining clarity
Cache System Prompts: Reuse system prompts across conversations

Pricing Structure

Model	Input (per MTok)	Output (per MTok)
Claude 3.5 Sonnet	$3.00	$15.00
Claude 3 Opus	$15.00	$75.00
Claude 3 Haiku	$0.25	$1.25

Use Haiku for simple tasks and reserve Sonnet/Opus for complex reasoning.

Integration Patterns

Multi-Model Workflows

Combine Claude with other models:

Claude for Analysis → GPT-4 for Code Generation
Claude for Research → GPT-3.5 for Summaries
Claude for Strategy → Specialized models for execution

Conversation Templates

Create reusable templates:

templates:
  - name: "Technical Review"
    system_prompt: "You are an expert code reviewer..."
    initial_message: "Please review the following code..."

  - name: "Business Analysis"
    system_prompt: "You are a strategic business consultant..."
    initial_message: "Analyze the following business scenario..."

Security Best Practices

Secure API Keys

Store API keys in environment variables or secure vaults, never in code or YAML files.

Content Filtering

Implement content moderation for user inputs and Claude responses.

Rate Limiting

Set organization-level rate limits to prevent abuse and control costs.

Audit Logging

Enable conversation logging for compliance and security monitoring.

Data Privacy

Review Anthropic’s data retention policy and configure accordingly.

Next Steps

LangChain Agents

Build agents with tools

Workflow Automation

Automate with n8n

Compare Models

Model selection guide

Analytics

Track performance

AI Providers

Workflow Automation

Advanced Integrations

​Overview

​Step 1: Create the AI Connection

​Get Your Anthropic API Key

​Add Connection in AgentFlow

​Step 2: Import Configuration via YAML

​Understanding YAML Structure

​YAML Configuration File

​Import Steps

​Step 3: Assign to a Group

​Create or Select a Group

​Assign the Model

​Step 4: Use in Chat

​Starting a Claude Conversation

​Best Use Cases

Complex Analysis

Technical Writing

Code Review

Long-form Content

​Example Interactions

​Advanced Configuration

​Model Variants

​Parameter Tuning

​Temperature (0.0 - 1.0)

​Top-K Sampling

​Stop Sequences

​System Prompts

​Troubleshooting

​Common Issues

​Error Response Handling

​Cost Management

​Token Optimization

​Pricing Structure

​Integration Patterns

​Multi-Model Workflows

​Conversation Templates

​Security Best Practices

​Next Steps

LangChain Agents

Workflow Automation

Compare Models

Analytics

Overview

Step 1: Create the AI Connection

Get Your Anthropic API Key

Add Connection in AgentFlow

Step 2: Import Configuration via YAML

Understanding YAML Structure

YAML Configuration File

Import Steps

Step 3: Assign to a Group

Create or Select a Group

Assign the Model

Step 4: Use in Chat

Starting a Claude Conversation

Best Use Cases

Example Interactions

Advanced Configuration

Model Variants

Parameter Tuning

Temperature (0.0 - 1.0)

Top-K Sampling

Stop Sequences

System Prompts

Troubleshooting

Common Issues

Error Response Handling

Cost Management

Token Optimization

Pricing Structure

Integration Patterns

Multi-Model Workflows

Conversation Templates

Security Best Practices

Next Steps