Skip to main content

​
AI Agent Workflow

Create an intelligent AI agent that remembers conversation history and can use tools.

​
What You’ll Build

A chatbot that:
  • Maintains conversation context across messages
  • Uses an AI model (OpenAI, Claude, or Gemini)
  • Responds via webhook

​
Prerequisites

  • MachinaOs running locally
  • An AI provider API key (OpenAI, Anthropic, or Google)

​
Step 1: Add the AI Agent

  1. Drag AI Agent from the AI Agents category
  2. This is the core of your intelligent assistant
The AI Agent node has multiple input handles:
  • Main Input (left) - Receives the user prompt
  • Memory Input (bottom-left diamond) - Connects to memory nodes
  • Model Input (top) - Optional model override

​
Step 2: Connect a Chat Model

  1. Drag OpenAI Chat Model (or Claude/Gemini) onto the canvas
  2. Connect it to the AI Agent’s model input (top handle)
  3. Configure the model:
Model: gpt-4o
Temperature: 0.7
Max Tokens: 1000
You can use any AI provider. Claude excels at reasoning, Gemini handles multimodal input.

​
Step 3: Add Conversation Memory

  1. Drag Simple Memory from AI Agents
  2. Connect it to the AI Agent’s memory input (bottom-left diamond handle)
  3. Configure:
Session ID: default
Memory Type: Buffer

​
Memory Types

TypeDescription
BufferKeeps all messages in the session
WindowKeeps only the last N messages
Memory is stored in SQLite and persists across server restarts.

​
Step 4: Add a Webhook Trigger

  1. Drag Webhook Trigger from Utilities
  2. Connect its output to the AI Agent’s main input
  3. Configure:
Path: chat
Method: POST

​
Step 5: Add a Webhook Response

  1. Drag Webhook Response from Utilities
  2. Connect the AI Agent’s output to Webhook Response
  3. Configure:
Status Code: 200
Body: {{aiAgent.response}}
Content Type: application/json

​
Complete Workflow

[Webhook Trigger] --> [AI Agent] --> [Webhook Response]
                         ^
                         |
               [Simple Memory]
                         ^
                         |
               [OpenAI Chat Model]

​
Step 6: Configure the Agent Prompt

Click on the AI Agent and set the system prompt: 
You are a helpful assistant. You remember our conversation history.
Be concise and friendly in your responses.

​
Step 7: Deploy and Test

  1. Click Deploy
  2. Test with curl:
# First message
curl -X POST http://localhost:3010/webhook/chat \
  -H "Content-Type: application/json" \
  -d '{"message": "Hi, my name is Alex"}'

# Second message (agent remembers your name)
curl -X POST http://localhost:3010/webhook/chat \
  -H "Content-Type: application/json" \
  -d '{"message": "What is my name?"}'
The agent should respond with your name, demonstrating memory!

​
Advanced: Multiple Sessions

Use different session IDs for different conversations: 
Session ID: {{webhookTrigger.body.user_id}}
This creates separate memory for each user.

​
Advanced: Window Memory

For long conversations, use Window mode to limit memory: 
Memory Type: Window
Window Size: 10
This keeps only the last 10 message exchanges.

​
Troubleshooting

  • Ensure Simple Memory is connected to the memory input (diamond handle)
  • Check that Session ID is consistent between requests
  • Memory is saved after each exchange automatically
  • Click the key icon in the toolbar
  • Add your API key for the provider you’re using
  • Keys are stored securely and encrypted

​
Next Steps

WhatsApp Automation

Connect your agent to WhatsApp

AI Models Reference

Compare AI providers