Reference
Article MarkdownReport an error

Action fastline_pro

System ID: action_fastline_pro

Description

Talks to a Fast Line Pro agent: sends a request, keeps conversation context via a constant, optionally files (vision), and blocking / streaming modes. The agent’s model and tools are set in the Fast Line Pro UI (Publish), not in the node JSON.

The response is stored in a constant (completion or save_response).

Events (scenario branches)

Event When it occurs
(response text) Success: the action returns the agent’s response text
error Missing agent_name / request / token, timeout, or service error

On success the branch is the response text itself. For stable branching use the save_response constant and the error branch.

Parameters

Parameter Type Required Default Description
agent_name string yes Fast Line Pro agent name
user_input string no message text User request. Supports placeholders
conversation_id string no null Constant name where the conversation ID is stored (not the ID itself)
reset_conversation string no If truthy — clears the conversation constant and starts a new one
inputs object no {} Extra variables for the agent
user string no current chat_id User identifier for the agent
mode string no "blocking" blocking or agent (streaming)
timeout_seconds number no 30 Timeout for streaming mode
vision_file boolean no false Process attached images/files
save_response string no "completion" Constant for the response

Configuration example

{
  "agent_name": "customer_support",
  "user_input": "{{user_question}}",
  "conversation_id": "fl_pro_conversation",
  "mode": "blocking",
  "timeout_seconds": 30,
  "save_response": "completion"
}
Using your own AI agent?Install the open skill so your AI agent can work with current official ConnectiveOne documentation.Get the skillNeed support?Couldn’t find the answer or need help from the ConnectiveOne team? Create a request in Client Portal.Create a request