Context transfer is a key feature in Atom that allows Smartons and other components to continue the conversation using the information that the user has already provided, avoiding repetitions and improving the conversational experience.

In this article, we explain what it is, how it works, when to activate or deactivate it, and how to avoid the most common errors.

Context transfer allows a Smarton or Response Evaluator to receive the original message from the client (or the information obtained in previous steps of the flow) and continue the conversation without losing previous information.

This happens transparently for the user, without them having to repeat what they already said.

It allows automatically transferring the client's message to the connected Smarton.

Simple example:

The client writes: "I am interested in the Mazda CX50"

The message matches an intent that redirects to a catalog Smarton

The Smarton receives that original message and responds:

"Perfect, here is all the information about the Mazda CX50. Would you like to schedule a test drive?"

👉 The user does not perceive the component change or need to repeat their query.

Context transfer is active by default for all platforms supported in the Inbound Flowbuilder (Bots):

You can view this configuration from the Bot's Start component, where you will see a visual indicator that shows that the functionality is active.

If you want to deactivate it, you simply have to turn off the corresponding toggle.

📌 Context transfer to Smartons occurs from an input component → Smarton.

Input → Smarton

Smarton → Action → Smarton

Example: Generic Smarton → stage → Field saving Smarton

In this case, the context is maintained between Smartons.

⚠️ The only action component that does NOT transfer context is the Message component.

Example:

Generic Smarton → Message → Smarton

👉 The flow stops at the message and the user must send a new input for the Smarton to activate.

When it comes to the user's first message and context transfer is active, that message will always look for the first input component, even if there are action or message components before it.

Example:

First message → Stage → Message → Evaluate Response

In this case, the initial message correctly reaches the evaluate response component.

If it were not the first message or the transfer was turned off, the flow would stop at the message component until a new response from the user is received.

There are scenarios where it is not recommended to transfer context:

In these cases, turning off context transfer helps to have greater control over the bot's behavior.

Context transfer allows:

The result: smarter bots and more human conversations.

This is one of the most common cases and usually occurs when context transfer is disabled.

If the user sends a message and the flow passes through a message component, the conversation stops there and does not continue to the Smarton, unless there is a new user input.

👉 Check that: