Skip to content
Sadia Khanam PrityAutomation Developer
AIAdvanced

AI Messenger Chatbot

A Facebook Messenger agent that answers product questions, takes orders and bookings, and hands off to a human when it should.

n8nMeta Graph APIGoogle GeminiGoogle SheetsGoogle Calendar

Problem

A retail page was getting messages around the clock. Replies during business hours were fine; everything outside that window sat unread for hours, and simple questions ate as much staff time as real ones.

Before

Every message — 'is this in stock', 'what's the price', a real order — waited in the same queue for a human to open Messenger.

After

The agent answers catalogue questions and takes orders and bookings immediately. It only escalates when a message genuinely needs a person.

Interactive workflow

Click through the actual node graph

Loading workflow…

Why this shape

Messenger webhooks arrive as two very different request types — Facebook's verification GET and the actual message POST — and Meta expects a 200 back within a few seconds or it starts retrying, which duplicates messages if the workflow is doing anything slow downstream. So the workflow answers the webhook immediately and does the real work after.

Image messages branch off before the text agent ever sees them — see Visual Product Search for that half.

What the AI Agent can actually do

The agent isn't just a language model with a system prompt. It has tools wired to it: it can read live product data, write orders and bookings to the same sheet the business already uses, book a calendar slot, and log a message for human follow-up when it decides a conversation is outside what it should handle on its own. Session memory keeps each customer's context across messages without mixing conversations together.

Impact

Replies in seconds instead of hours; simple orders and bookings no longer need a human at all.

Start a similar project