WABridges
Guide

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 — WA Bridges handles the WhatsApp connection, you handle the logic.

Start free → View API docs

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.

WA Bridges 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.

How it works

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.
4
Send rich replies
Reply with text, images, audio, documents, polls, or location pins. The same API handles all media types.

What you can build

🧠
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 into any AI assistant → get working code in your language.
I want to build a WhatsApp chatbot using WA Bridges for the WhatsApp
connection and an AI model to generate replies.

My stack: [Node.js — update this]
My setup:
- WA_API_KEY: my WA Bridges 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 WA Bridges
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 WA Bridges send API
5. The webhook must respond quickly — process the AI call asynchronously

Please read the WA Bridges API docs before writing:
https://wabridges.com/docs.txt

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

Why WA Bridges