> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.flockx.io/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.flockx.io/_mcp/server.

# Connecting Your Flockx Agent to Make.com: Technical Integration Guide

> Enabling automated workflows triggered by your agent's intelligence.

FlockX's powerful AI agents can be extended beyond the platform through integration with Make.com. This guide walks you through the process of connecting your FlockX agent to Make.com, enabling automated workflows triggered by your agent's intelligence.

## Core API Connectivity

### Prerequisites

Before connecting your agent to Make.com, you'll need:

1. **Your FlockX API Token** - [how to get your api key](https://docs.flockx.io/documentation/getting-started/api-authentication)
2. **Your Agent's UUID** - Your agent's unique identifier (format: `e151675f-2d7c-46ee-a2a1-d68529adcb3d`). You can find this in the web url of your browser e.g. [https://flockx.io/workbench/agents?agentId=82eee21b-089c-4aa5-b9a0-923c61ae712g](https://flockx.io/workbench/agents?agentId=82eee21b-089c-4aa5-b9a0-923c61ae712g)
3. **A Make.com account** - Free or paid, depending on your automation needs

### FlockX Agent API Endpoint

The primary endpoint for agent interaction is:

```
https://api.flockx.io/api/v1/agents/{agent-id}/prompt
```

This endpoint accepts POST requests and returns your agent's response.

### Required Headers

Every API request to FlockX requires these headers:

```
Authorization: Token your-api-token-here
X-Twin: your-agent-uuid-here
Content-Type: application/json
```

### Request Body Structure

The basic request body is simple:

```json
{
  "prompt": "Your instruction or query for the agent"
}
```

### Response Format

The API returns a JSON response containing your agent's reply:

```json
{
  "message": "Your agent's response based on its knowledge"
}
```

## Setting Up Make.com Integration

### Basic Make.com Scenario Creation

1. **Log in to your Make.com account**
2. **Create a new scenario**
3. **Select a trigger module** that will initiate your workflow

Common triggers include:

* Webhooks (for form submissions, external systems)
* Scheduled events (for regular agent interactions)
* App-specific triggers (Gmail, Slack, etc.)

### Configuring the HTTP Module for FlockX

After your trigger module, add an HTTP module:

1. **Click the "+" icon** after your trigger module
2. **Search for and select the "HTTP" module**
3. **Configure the HTTP module**:
   * **URL**: `https://api.flockx.io/api/v1/agents/{your-agent-id}/prompt`
   * **Method**: POST
   * **Headers**:
     ```
     Authorization: Token {{your-api-token}}
     X-Twin: {{your-agent-uuid}}
     Content-Type: application/json
     ```
   * **Body (type)**: JSON
   * **Body (content)**:
     ```json
     {
       "prompt": "Your prompt text, which can include variables from previous modules"
     }
     ```
   ```
   ```

![Sample image](https://res.cloudinary.com/fetch-ai/image/upload/v1748614671/flockx-community-app/Docs/Screenshot_2025-05-30_at_2.47.03_PM_jrcror.png)

### Processing the Agent's Response

Add modules after the HTTP request to process and use your agent's response:

1. **JSON Parser module** (optional): If you need to extract specific parts of the response
2. **Action modules**: Email, SMS, CRM updates, etc.

## Example Make.com Scenarios

### Scenario 1: Automated Quote Generation

**Trigger**: Webhook (Form Submission)

1. **Webhook**: Receives customer data from a quote request form
2. **HTTP Request to FlockX**:
   ```json
   {
     "prompt": "Generate a personalized quote for {{1.data.name}} who is interested in {{1.data.service}}. Their budget is {{1.data.budget}} and timeframe is {{1.data.timeframe}}. Include pricing details and next steps."
   }
   ```
3. **Email**: Send the agent's response to the customer
4. **CRM Update**: Create a new lead with the quote information

### Scenario 2: Scheduled Follow-Up System

**Trigger**: Scheduler (Runs daily)

1. **Scheduler**: Triggers at 9 AM daily
2. **Google Sheets**: Get list of quotes sent 48 hours ago without response
3. **Iterator**: Loop through each pending quote
4. **HTTP Request to FlockX** for each pending quote:
   ```json
   {
     "prompt": "Create a friendly follow-up email for {{3.customer_name}} who received a quote for {{3.service}} 2 days ago at {{3.quote_amount}}. Add value by mentioning a benefit they might not have considered."
   }
   ```
5. **Email**: Send personalized follow-up with agent's response
6. **Google Sheets**: Update follow-up date in tracking sheet

## Advanced Make.com Integration Techniques

### Decision Routing Based on Agent's Response

Use Router modules to create conditional workflows based on your agent's response:

1. **HTTP Request to FlockX**: Get agent response
2. **Text Parser**: Extract key information or intent
3. **Router**:
   * Route 1: Response contains "urgent" → Send SMS notification
   * Route 2: Response contains "booking" → Create calendar event
   * Route 3: Default → Standard email response

Implementation example:

```
Router setup:
- Filter 1: {{2.parsedResponse.contains("urgent")}}
- Filter 2: {{2.parsedResponse.contains("booking")}}
- Default route for other cases
```

### Enhanced Context Building

Gather information from multiple sources before querying your agent:

1. **Multiple information modules**: CRM, Calendar, Database
2. **Array Aggregator**: Combine data from multiple sources
3. **Text Formatter**: Structure the aggregated data
4. **HTTP Request to FlockX**:
   ```json
   {
     "prompt": "Customer: {{1.customer_data.name}} (Previous purchases: {{2.purchase_history}}) Current request: {{3.current_inquiry}} Current account status: {{4.account_status}} Provide a personalized response that addresses their needs and account history."
   }
   ```

### Implementing Multi-Step Conversations

For scenarios requiring back-and-forth communication:

1. **Initial Trigger**: Webhook or app notification
2. **Database Module**: Retrieve conversation history
3. **HTTP Request to FlockX**:
   ```json
   {
     "prompt": "This is a continuation of a conversation. Previous messages: {{3.conversation_history}} New message from customer: {{1.new_message}} Respond appropriately with full context."
   }
   ```
4. **Database Module**: Store updated conversation history
5. **Response Module**: Send agent's reply to appropriate channel

## Best Practices for Make.com Integration

### Security

* Store your API token and agent UUID as Make.com **Data Stores** or **Scenario Variables**
* Implement error handling for API failures
* Set up notifications for failed runs

### Performance

* Use **Aggregators** for batch processing when possible
* Implement **Filters** to avoid unnecessary processing
* Consider scenario execution limits based on your Make.com plan

### Prompt Engineering

* Structure prompts consistently
* Include all necessary context in each prompt
* Use variables to personalize agent interactions

### Monitoring and Optimization

* Use Make.com's built-in **Logging** for troubleshooting
* Set up **Alerts** for critical failures
* Review and refine prompts based on agent performance

## Troubleshooting Common Issues

| Issue                  | Possible Solution                                              |
| ---------------------- | -------------------------------------------------------------- |
| 401 Unauthorized       | Verify API token is correct in your HTTP module                |
| Timeout errors         | Consider breaking complex scenarios into multiple smaller ones |
| Rate limiting          | Add delay modules between consecutive API calls                |
| Data formatting issues | Use text parser modules to clean input data                    |
| Inconsistent responses | Review and refine your prompt structure                        |

## Next Steps

After implementing your basic integration, consider these advanced capabilities:

1. **Implement two-way communication flows**: Allow your agent to both receive and send information
2. **Create scheduled maintenance tasks**: Automate regular agent knowledge updates
3. **Build analytics dashboards**: Track agent performance metrics
4. **Implement approval workflows**: Add human oversight for critical decisions

By connecting your FlockX agent to Make.com, you'll unlock powerful automation capabilities that extend your agent's intelligence across your entire business ecosystem.

# Connecting Your FlockX Agent to n8n: Technical Integration Guide

FlockX's AI agents can be seamlessly integrated with n8n to create powerful, automated workflows. This guide provides step-by-step instructions for connecting your FlockX agent to n8n, enabling your agent to interact with external systems and trigger automated processes.

## Core API Connectivity

### Prerequisites

Before connecting your agent to n8n, you'll need:

1. **Your FlockX API Token** - Used for authentication
2. **Your Agent's UUID** - Your agent's unique identifier (format: e.g., `e151675f-2d7c-46ee-a2a1-d68529adcb3d`)
3. **An n8n instance** - Self-hosted or cloud-based

### FlockX Agent API Endpoint

The primary endpoint for agent interaction is:

```
https://api.flockx.io/api/v1/agents/{agent-id}/prompt
```

This endpoint accepts POST requests and returns your agent's response.

### Required Headers

Every API request to FlockX requires these headers:

```
Authorization: Token your-api-token-here
X-Twin: your-agent-uuid-here
Content-Type: application/json
```

### Request Body Structure

The basic request body is simple:

```json
{
  "prompt": "Your instruction or query for the agent"
}
```

### Response Format

The API returns a JSON response containing your agent's reply:

```json
{
  "message": "Your agent's response based on its knowledge"
}
```