Connecting Your First AI Endpoint

Connect your AI service, workflow, or custom endpoint to AgentFlow. AgentFlow works with ANY AI endpoint that can receive webhooks and return responses—including OpenAI, Anthropic, custom AI services, N8N workflows, Make.com automations, and more.

Prerequisites

Before you start, you’ll need:

✅ AgentFlow organization created
✅ An AI endpoint URL (OpenAI API, custom webhook, etc.)
✅ Authentication credentials (API key, bearer token, etc.)
✅ Admin access to your organization

Step 1: Access the Admin Panel

After creating your organization, navigate to the admin panel:

Click your organization name in the top navigation
Select “Admin Panel” from the dropdown
You’ll see tabs for Analytics, Models, Groups, and Users

Step 2: Start Connection Configuration

Go to Models Tab

Click the “Models” tab in the admin panel (this configures your AI connections)

Click Add Model

Click the ”+” (plus) button to start adding a new connection

The “Models” tab is where you configure all AI connections—whether they’re AI model APIs, workflows, or custom endpoints.

Step 3: Basic Information

Fill in the essential details for your AI connection:

Required Fields

Name *

Example: "GPT-4 Assistant"
A descriptive name shown in the model selection interface

Endpoint *

Example: "https://api.openai.com/v1/chat/completions"
The complete URL where POST requests will be sent
Must include protocol (https://)

Optional Fields

Model ID

Example: "gpt-4-assistant"
Auto-generated from name if left empty
Used for API calls and internal references

Schema

Example: "v1.0"
Optional version identifier for tracking API versions

Description

Example: "GPT-4 model for complex reasoning and analysis"
Brief explanation of what this model does

Request Headers

Add authentication headers required by your endpoint:

OpenAI Example

Key: Authorization Value: Bearer sk-...your-api-key...

Custom API Example

Key: X-API-Key Value: your-custom-token

Headers containing sensitive data (authorization, api-key, secret) are automatically masked for security.

To add headers:

Click “Add Header”
Enter the header key (e.g., “Authorization”)
Enter the header value (will be masked if sensitive)
Repeat for additional headers
Click ”×” to remove unwanted headers

Suggestion Prompts

Add up to 3 suggested prompts to help users understand what your model can do: Examples:

"Analyze the sentiment of this customer review"
"Summarize this document in 3 bullet points"
"Generate creative product name ideas"

These appear in the chat interface to guide users.

Step 4: Field Mapping

Important: AgentFlow works with ANY endpoint that can respond to webhooks—not just pre-configured AI models.

What You Can Connect

AI APIs

OpenAI (GPT-4, GPT-3.5)
Anthropic (Claude)
Google (Gemini)
Custom AI services

Automation Tools

N8N workflows
Make.com scenarios
Zapier webhooks
Custom integrations

Agent Builders

ChatGPT Agent Builder
Custom agent endpoints
LangChain applications
AutoGPT instances

Any Webhook

HTTP endpoints
Serverless functions
Microservices
Custom APIs

Map your request and response fields to match your endpoint’s expected format. This step varies by endpoint type—refer to your endpoint’s documentation.

Step 5: Request Template

Configure how messages are sent to your endpoint.

Input Configuration

Define the request body structure: For OpenAI-style APIs:

{
  "messages": [
    {"role": "user", "content": "{{user_message}}"}
  ],
  "model": "gpt-4"
}

For custom endpoints:

{
  "input": "{{user_message}}",
  "parameters": {
    "temperature": 0.7,
    "max_tokens": 2000
  }
}

AJV Schema Validation

Add JSON Schema validation for your request/response format.

What is AJV? AJV (Another JSON Validator) ensures your requests and responses match the expected format, catching errors before they cause issues.Learn more: AJV Documentation

Example AJV Schema:

{
  "type": "object",
  "properties": {
    "messages": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "role": {"type": "string"},
          "content": {"type": "string"}
        },
        "required": ["role", "content"]
      }
    },
    "model": {"type": "string"}
  },
  "required": ["messages", "model"]
}

Test Variables

Provide sample data to test your configuration: Sample Payload:

{
  "messages": [
    {"role": "user", "content": "Hello, how are you?"}
  ],
  "model": "gpt-4"
}

Validate: Click “Validate” to ensure your configuration is correct.

Step 6: Test Endpoint

Critical: AgentFlow requires your endpoint to work before saving the configuration.

Run Test

Click “Run Test” to send a request to your endpoint

Check Response

You should see a 200 (Success) response

Fix if Needed

If you get any other status code, review and fix your configuration

Retry

Keep testing until you get a successful response

AgentFlow will NOT allow you to save a connection that doesn’t work. This ensures users can always rely on functional AI endpoints.

Response Status Codes:

Code	Meaning	Action
200	✅ Success	Proceed to next step
401	❌ Unauthorized	Check your API key/auth headers
404	❌ Not Found	Verify endpoint URL is correct
500	❌ Server Error	Check endpoint is online and working

Step 7: Define Output

Parse the response from your endpoint to extract the agent’s message.

Nested JSON Route

Specify the path to the message content in the response: OpenAI Response Example:

{
  "choices": [
    {
      "message": {
        "content": "Hello! I'm doing great, thanks for asking!"
      }
    }
  ]
}

JSON Path:

choices[0].message.content

Custom Endpoint Example:

{
  "output": {
    "response": "Your message here"
  }
}

JSON Path:

output.response

The JSON path tells AgentFlow where to find the agent’s response text in your endpoint’s response.

Step 8: Create Group & Assign Access

Before you can use your AI connection, you must create a group and assign permissions:

Go to Groups Tab

Click the “Groups” tab in the admin panel

Create New Group

Click “Create Group” button

Name: e.g., “GPT-4 Users”
Description: Who should have access

Add Connection to Group

Find your newly created AI connection
Check the box to add it to this group

Add Yourself to Group

Find your user in the members list
Add yourself to the group

Why groups? Groups control access to AI connections. Only users in a group can see and use the connections assigned to that group.

Step 9: Start Conversing

Now you’re ready to use your AI connection!

Go to the Chat page
Click “New Conversation”
Select your AI connection from the dropdown
Start chatting!

Next: Start Your First Conversation

Learn how to use your newly connected AI endpoint

Configuration Examples

OpenAI GPT-4

Name: GPT-4 Assistant
Endpoint: https://api.openai.com/v1/chat/completions
Headers:
  - Authorization: Bearer sk-...
  - Content-Type: application/json

Request Template:
  {
    "model": "gpt-4",
    "messages": [{"role": "user", "content": "{{message}}"}]
  }

Output Path: choices[0].message.content

Anthropic Claude

Name: Claude Sonnet
Endpoint: https://api.anthropic.com/v1/messages
Headers:
  - x-api-key: sk-ant-...
  - anthropic-version: 2023-06-01
  - Content-Type: application/json

Request Template:
  {
    "model": "claude-3-sonnet-20240229",
    "messages": [{"role": "user", "content": "{{message}}"}],
    "max_tokens": 4096
  }

Output Path: content[0].text

Custom N8N Workflow

Name: Custom Support Agent
Endpoint: https://n8n.yourcompany.com/webhook/support-agent
Headers:
  - X-API-Key: your-webhook-secret

Request Template:
  {
    "input": "{{message}}",
    "context": "customer_support"
  }

Output Path: response

Troubleshooting

Test returns 401 Unauthorized

Problem: Authentication failedSolutions:

Verify API key is correct
Check header key name (e.g., “Authorization” vs “X-API-Key”)
Ensure “Bearer ” prefix for OpenAI
Check if API key has expired

Test returns 404 Not Found

Problem: Endpoint URL is incorrectSolutions:

Double-check the endpoint URL
Ensure it includes https://
Verify the path is correct (/v1/chat/completions)
Test the URL in Postman or curl first

Test returns 500 Server Error

Problem: Endpoint or service is having issuesSolutions:

Check if the service is online
Verify your request format matches their API
Test with their official documentation examples
Contact the service provider’s support

Can't see connection in chat

Problem: Missing group assignmentSolutions:

Go to Groups tab
Create a group if you haven’t
Add the AI connection to the group
Add yourself as a member of that group

Response parsing fails

Problem: Wrong output pathSolutions:

Check the actual response structure from test
Use browser console to inspect response
Verify JSON path syntax (e.g., choices[0].message.content)
Test the path with a JSON path validator

What’s Next?

Choose AI Connections

Understand which connection types work best

Advanced Configuration

Fine-tune your connection with advanced settings

Test Your Connection

Best practices for testing before deployment

Start Conversations

Begin using your AI connections

Need Help?

Contact support@agentflow.live for assistance with connecting AI endpoints

Getting Started

AI Agents

Conversations

Organization

Agent Distribution

Analytics & Insights

Security & Privacy

Support

​Connecting Your First AI Endpoint

​Prerequisites

​Step 1: Access the Admin Panel

​Step 2: Start Connection Configuration

​Step 3: Basic Information

​Required Fields

​Optional Fields

​Request Headers

OpenAI Example

Custom API Example

​Suggestion Prompts

​Step 4: Field Mapping

​What You Can Connect

AI APIs

Automation Tools

Agent Builders

Any Webhook

​Step 5: Request Template

​Input Configuration

​AJV Schema Validation

​Test Variables

​Step 6: Test Endpoint

​Step 7: Define Output

​Nested JSON Route

​Step 8: Create Group & Assign Access

​Step 9: Start Conversing

Next: Start Your First Conversation

​Configuration Examples

​OpenAI GPT-4

​Anthropic Claude

​Custom N8N Workflow

​Troubleshooting

​What’s Next?

Choose AI Connections

Advanced Configuration

Test Your Connection

Start Conversations

Need Help?

Connecting Your First AI Endpoint

Prerequisites

Step 1: Access the Admin Panel

Step 2: Start Connection Configuration

Step 3: Basic Information

Required Fields

Optional Fields

Request Headers

Suggestion Prompts

Step 4: Field Mapping

What You Can Connect

Step 5: Request Template

Input Configuration

AJV Schema Validation

Test Variables

Step 6: Test Endpoint

Step 7: Define Output

Nested JSON Route

Step 8: Create Group & Assign Access

Step 9: Start Conversing

Configuration Examples

OpenAI GPT-4

Anthropic Claude

Custom N8N Workflow

Troubleshooting

What’s Next?