Skip to content
Menu

Search the site

Type to search guides, blog, API and product.

↑ ↓ to move · Enter to open · Esc to close

Help center

How to capture customer data with forms in the conversation

TBit forms capture structured data (name, email, city) right in the conversation, question by question and with validation, without sending the customer to an external link.

5 min read

How to capture customer data with forms in the conversation

What it does

Forms capture structured customer data: name, email, city, size, whatever the business needs. The agent fills them out by chatting, question by question, without sending the customer to an external link.

How it works

Each form defines its fields (text, number, options, date) and which ones are required. When the conversation calls for it, the agent asks for the data one at a time, validates what it receives and saves the complete answer. Forms also work outside the chat: they can be shared through a link or embedded on a web page.

Where you set it up

Menu Forms: create the form, define fields and see the answers received. The data captured also feeds the contact profile, visible in the conversation in Chats.

What NOT to put in the prompt

The list of fields to ask for ("ask for name, then email, then city"). That's a form: you create it once and the agent runs it with validation. The prompt can say when to use it, for example "before quoting, complete the contact data form".

Train with your own AI

Do you use ChatGPT or Claude? Connect them to your TBit agent and let them help you train it with your real data: on the platform go to Agent settings, Connect your AI section, generate your token and add the connector https://api.tbit.app/mcp. Your assistant can review the prompt, the memories and recent conversations, and suggest improvements.