Does the agent move contacts between stages on its own?

Yes, based on what happens in the chat. Your team can also drag the card on the board or change the stage from the conversation.

Can I define my own stages?

Yes. You create the stages your business uses (new, interested, quoted, closed or others) and order them in the Pipeline menu.

How do I tell the agent when to move a sale forward?

With a short criterion in the prompt, for example "when the customer asks for a price, mark them as interested". The process definition lives in the Pipeline, not in the prompt.

Help center

Sales pipeline: how AI moves your contacts through each stage

TBit's pipeline organizes contacts by stage (new, interested, quoted, closed) and the agent moves them as the conversation progresses. It gives you visibility into every sale.

Published on July 18, 2026Updated on October 10, 20265 min read

What it does

The pipeline organizes contacts by stage: new, interested, quoted, closed, or whatever stages your business defines. It gives you visibility into where each sale stands and what's going cold.

How it works

Stages are defined once, in order. As the conversation progresses, the contact moves from stage to stage, either by the agent based on what happens in the chat or by your team dragging the card on the board. The board shows all contacts by column, with their conversation one click away.

Where to set it up

Pipeline menu: create the stages, order them and see the board with your contacts. From the conversation in Chats you can also change a contact's stage by hand.

What NOT to put in the prompt

Long definitions of your sales process ("our stages are..."). The stages live in the Pipeline. The prompt can give criteria for moving forward, for example "when the customer asks for a price, mark them as interested", written short and clear.

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.