Home Getting to Know Controlled Flows How the ClaudIA and Controlled Flow Interaction Works

How the ClaudIA and Controlled Flow Interaction Works

Last updated on Aug 29, 2026

Interaction: Customer <-> ClaudIA <-> Controlled Flow

Detailed Flow Explanation

Customer sends a message:

The customer initiates contact by sending a message to ClaudIA. The message can be a simple question, an inquiry about an order status, or a more specific question that requires an automated flow.

ClaudIA interprets the message

Upon receiving the message, ClaudIA, powered by a GPT-based model, begins processing the content. The model conducts a deep linguistic analysis to understand the customer's intent, the message context, and to identify important entities.

ClaudIA checks the type of content

With the message processed, ClaudIA determines what type of response is necessary:

  • Content N1: if the message is simple and straightforward, ClaudIA responds automatically with an answer from the knowledge base.

  • Content N2: if the question is more complex or requires human assistance, ClaudIA transfers the conversation to the N2 team.

  • Interactive Content: if the inquiry involves a more complex request (e.g., checking order status, API-based information retrieval, or Google Sheets integration), ClaudIA activates the Controlled Flow.

Controlled Flow (Interactive Content)

When the content is interactive, ClaudIA triggers the Controlled Flow. This flow can include:

  • Queries (API, Google Sheets, LLM prompt, tree flows, JavaScript, etc.): The Controlled Flow performs the defined queries, such as checking order status or retrieving specific data.

  • Response Generation: The response generated by the Controlled Flow is then sent to the customer.

Flow Completion

After the Controlled Flow execution, the interaction can proceed in different ways:

  • Return to ClaudIA: if configured, the flow returns to ClaudIA, which continues the interaction. "End Flow [N1]".

  • Escalated to N2: if set up, the conversation is escalated to the N2 team for more in-depth support "Forward to Human [N2]".