Agent Router
Agent Router decides which way the flow continues. You define a list of intentions (for example “Quote”, “Issue” or “Other request”) with a description of each one. When a message arrives, the AI model reads it, decides which intention it matches and sends it, unchanged, through that intention’s output. The other outputs do not continue.
It is an older component kept for compatibility with existing flows. For new flows, use Router Agent.
When to use it
- Maintaining existing flows built with this component.
- Splitting customer messages into sales, support and billing.
- Choosing which specialised agent handles each conversation.
Configuration
| Connection | What to connect |
|---|---|
| Data Input | The message or data to classify, for example from Chat Input. |
| Model (required) | The AI model that analyses the intention. |
| Field | What it does |
|---|---|
| Number of Intentions (required) | How many intentions you want to tell apart. At least 2. Default: 2. Changing it adds or removes the field groups of each intention and their outputs. |
| System Prompt | Extra classification instructions, for example criteria for borderline cases. |
| Name (required, one per intention) | The intention’s name. It is also the name of its output on the canvas. |
| Description (one per intention) | When this intention should be chosen. The clearer it is, the better the model classifies. |
Each intention appears as a group Intention 1, Intention 2, and so on, with its Name and Description fields.
The default intention. If an intention’s name or description contains words such as “default”, “fallback”, “catch-all”, “other”, “else”, “defecto”, “por defecto”, “predeterminado” or “otro”, that intention receives the messages that match no other. If there is no default intention and a message matches none, it does not continue through any output.
Advanced options
| Field | What it does |
|---|---|
| Confidence Threshold | An inherited field with the value 0.7. It currently does not change the classification. |
| Use memory | Keeps the conversation state between messages. Turning it on shows the Memory connection, to keep the conversation in a memory component of your own, and the Memory Strategy and Memory Limit fields, which set how the history is trimmed. Default: off. |
Output
One output per intention, named after what you wrote in Name. Only the output of the detected intention delivers the original message; connect each one to the part of the flow that should handle that case, for example a specialised Agent.
Example
The renovation company Obras Prisma receives requests by chat. It sets up the component like this:
- Connect Chat Input to Data Input and an AI model to Model.
- Set Number of Intentions to 3 and fill in:
- Name: Quote. Description: The customer wants a price or a quote for a job.
- Name: Issue. Description: The customer has a problem with an ongoing or finished job.
- Name: Other request. Description: Default intention for any other message.
- Connect the Quote output to an agent that collects the job details, Issue to an agent that opens a ticket, and Other request to a general assistant.
Good practices
- Always include a default intention so no message is left unanswered.
- Write descriptions that do not overlap: if two intentions are similar, the model hesitates.
Related components
- Router Agent: the current version of this component.
- Supervisor Agent: distributes the request among agents without splitting the flow into branches.