Build your WhatsApp bot with the Code Agent

The Code Agent is the primary way you build and modify your bot in Paige. You describe what you want your bot to do in plain language, and the agent writes or edits the underlying bot code for you. It has direct access to your project files, database, and WhatsApp tools, so it can make end-to-end changes — from creating a new conversation state to uploading a Flow to Meta — without you touching a code editor.

​

How it works

When you open the AI chat for a project, the agent has context about your current bot code and can read, write, and edit files in your project. You describe a change, the agent makes it, and can immediately test it by sending a message through the bot’s preview mode. You stay in the loop through a task list the agent maintains while working through multi-step changes.

​

What the Code Agent can do

The agent has access to a set of built-in tools it uses behind the scenes to complete your requests.

​

It knows what you’ve actually connected

Two details worth knowing, because they change what the agent tells you. It looks things up rather than guessing. Before writing any Airtable or Slack code, the agent fetches the real reference — for Airtable, that includes a snapshot of your actual base, so it uses your real table and field names rather than plausible-sounding invented ones. It knows whether you’re connected. Paige tells it, rather than letting it assume. So if you ask for Airtable code without an Airtable connection, it writes the code and then tells you plainly that you need to connect Airtable before the bot will work — instead of cheerfully reporting success on something that can’t run.

​

The knowledge base

Your bot can answer from your own documents — your menu, your policies, your FAQs, your price list. Add one by attaching it in chat with the paperclip, or uploading it in Tools → Storage. Paige reads PDFs, Word documents, and text files, and your bot can then answer questions from them. Keep these focused. Everything you add is read on every question your bot answers, so a tight FAQ works better than a long brochure — for cost as well as accuracy.

​

How a new bot starts

When you ask the Code Agent to build a new bot, it begins from one of two starter templates depending on the kind of bot you want.

• An AI-driven bot — uses an AI router to classify each message and respond conversationally, with structured states for collecting information and handling support.
• A simple menu bot — a pure state machine with no AI inside the bot itself; responses are predictable and deterministic. Best for menu-driven flows.

Both templates ship with the same core capabilities (messaging, database, logging) so you can switch direction at any time by chatting with the agent.

​

State machine pattern

Your bot manages each conversation as a state machine. Every conversation has a current state, and each incoming message is handled by the code for that state. There are two kinds of states:

• SEND states — send a message or UI element, then immediately transition to an AWAIT state
• AWAIT states — receive the user’s response and process it

To add a new conversation state, tell the agent what you want. For example:

“Add a booking flow. After the user selects ‘Book a demo’, ask for their name, then their preferred date, then confirm the booking and save it to a bookings table.”

The agent will:

1. Create the bookings table in your database
2. Add the conversation states needed to walk the user through name → date → confirmation
3. Wire up the transitions between states
4. Test the full flow in preview mode

​

Prompting the agent well

How you phrase a request has a real effect on the result — and the agent behaves differently in a brand-new project than in one that already has a bot. Both are covered on a dedicated page.