WABridges
AI agents

Build a WhatsApp AI chatbot
in an afternoon.

Receive every inbound message as a webhook. Reply via REST API. Plug in GPT, Claude, or any AI model, WABridges handles the WhatsApp connection, you handle the logic.

Start free All guides →

WhatsApp is where your users already are. Building a bot for it shouldn't require a business account approval, a 90-day review process, or per-message billing that scales against you.

WABridges gives you a real WhatsApp number under full API control. Inbound messages arrive as webhooks. Replies go out as REST calls. Everything between is yours to build.

Four steps. One loop.

We keep the number online and hand you every event. You write the part in the middle.

1
Provision a bridge

Create a bridge with a POST request. Pair it with any WhatsApp number, personal or dedicated SIM.

2
Configure your webhook

Set a webhook URL on your bridge. Every message sent to your WhatsApp number hits that endpoint as a POST with a JSON payload.

3
Run your bot logic

Parse the message, run it through your AI model or decision tree, then POST the reply to the send endpoint. The whole loop takes milliseconds.

Send rich replies

Reply with text, images, audio, documents, polls, or location pins. The same API handles all media types.

The same three calls. Different jobs.

Every loop below is the one above with your own logic in the middle.

🧠 AI chatbot
  • Pipe messages to any LLM
  • Maintain conversation context
  • Tool calls and function use
  • Automatic language detection
🌳 Decision-tree bot
  • Menu-driven flows
  • FAQ auto-responder
  • Lead qualification
  • Appointment booking
🎮 Games & communities
  • Trivia bot
  • Word games in group chats
  • Daily quiz broadcasts
  • Leaderboards via replies
🔗 Integration bot
  • Query your database
  • Trigger Zapier/Make
  • GitHub issue reporter
  • Internal ops bot

Paste into Claude, ChatGPT, or any AI assistant

Copy this prompt, paste it into any AI assistant, get working code in your language.

prompt 
I want to build a WhatsApp chatbot using WABridges for the WhatsApp
connection and an AI model to generate replies.

My stack: [Node.js: update this]
My setup:
- WA_API_KEY: my WABridges API key
- OPENAI_API_KEY: my OpenAI key (or tell me how to swap for another model)
- Bridge customer_ref: "my-bot"

I need:
1. A webhook endpoint that receives inbound messages from WABridges
2. Conversation history tracked per chat_id (in-memory is fine to start)
3. Each message sent to gpt-4o-mini with a system prompt I can customize
4. The AI reply sent back via the WABridges send API
5. The webhook must respond quickly, process the AI call asynchronously

Please read the WABridges API docs before writing:
https://wabridges.com/llms-full.txt

Keep it under 60 lines if possible. Add a comment where I should
customize the system prompt.

One number, one price, no approval queue.

What you get on the WhatsApp side, whatever you build on yours.

No template pre-approval: respond to any message immediately
Works with any AI: GPT, Claude, Gemini, Llama, local models
Group chat support: deploy bots inside existing group conversations
Send text, images, audio, documents, polls, and location pins
Flat $5/month: no per-message cost, no matter how chatty
Multi-bridge: run different bots on different numbers in parallel

Next, from the same three calls.

Other guides that build on the loop you just read.

Connect WhatsApp to Claude. Put Claude on a real WhatsApp number in under an hour. Inbound messages arrive as webhooks, Claude's replies go back via REST. Guide Support customers where they already are. Let customers message you on WhatsApp. Receive messages as webhooks, reply via API. Guide A "Connect WhatsApp" button, living inside your app. Drop a 'Connect WhatsApp' button into your product and let customers pair their own number without leaving your UI. Guide

Choosing a provider? See how WABridges compares to Twilio, 360dialog, and other WhatsApp API providers.