Router Nodes¶

Routers¶

Router nodes are decision points in your pipeline. Instead of following one fixed path, a pipeline with a router can choose different paths based on what the participant says or what your system already knows about the participant.

In simple terms, a router checks the current conversation context and sends the input (participant message plus available data) to the most relevant downstream node. This allows your chatbot to adapt in real time.

For example:

1. Participant Status (Data-Based): You can route new participants to a specialized onboarding flow while returning participants are sent straight to the main menu.

2. Topic Expertise (Intent-Based): You can detect when a participant is asking about a complex technical issue and route that message to a specialist node instead of a general FAQ node.

Useful Terms¶

1. Linked Downstream Node: Any node that appears after the current node in the pipeline flow.

2. Conversation Context: The total set of information available to the pipeline at that moment. This includes the participant’s current message, their chat history (as determined by the router's own History setting), and known data (like whether they are a "new" or "returning" participant).

3. Default Path: The "safety net" route (marked with a blue *). If the router cannot confidently decide where to send the participant, it follows this path to prevent the conversation from breaking. more.

Router Types¶

There are two distinct ways to route a conversation in OCS. The choice depends on whether you are routing based on what the participant means or what the system knows.

LLM Router Node¶

The LLM Router uses an AI model to read the incoming message and classify its intent.

• How it works: It acts as a classifier. You provide a prompt that tells the LLM how to categorize a message (for example, "If the participant is angry, output ESCALATE").
• Best for: Handling unpredictable participant text.
• You define output keywords for your downstream paths. If the LLM outputs BILLING, the conversation follows the path labeled BILLING to the next downstream node.

See a working example in the Chatbot Workflow Cookbook, where an LLM Router classifies input into GENERAL, ROLEPLAY, and QUIZ paths.

Static Router Node¶

The Static Router does not use an AI model and does not read the participant's message. Instead, it looks up a specific value stored in your data source.

• How it works: It checks a pre-existing key or tag, such as participant profile data or session information, and follows the matching path.
• Best for: Routing based on known attributes like preferred language, subscription tier, or VIP status.
• Example: If your data shows subscription_tier = premium, the Static Router immediately sends the participant to the Priority Support Agent.