Skip to main content
Version: Current

AI Agent

version: Enterprise Mode: Streaming Mode: Request-Response

Description

Runs an LLM agent using the task prompt and available tools, returning either text or structured output. The component is available after at least one AI integration is configured in the Admin Panel.

Parameters and configuration

NameDescription
LLM IntegrationLLM integration to use.
Chat model nameThe chat model to use. The available models depend on the LLM Integration selected.
PromptDescription of the concrete task to be performed.
MCP tools accessYou can choose here which tools exposed by the defined MCP integrations can be used.
Output variable nameVariable name under which node result will be available in a subsequent nodes.

Advanced parameters:

NameDescription
System messageReusable rules that define how the agent should behave. Some AI agents providers use 'agent instructions' term here.
Max iterationsMaximum reasoning/tool-use loop count.
Structured outputOptional; json schema of the desired response.
TemperatureTemperature is a hyperparameter that controls the randomness of text generation. Lower values (e.g., 0.2) make the model’s output more focused and deterministic by favoring the most likely tokens, while higher values (e.g., 0.8 or above) produce more diverse and creative responses by flattening the probability distribution.

Returned value

This component returns response as a JSON object or text.

Additional considerations

  • You can use string template during prompt creation to use data available in the scenario (e.g., documents retrieved from the vector store)
  • Currently only selected models are available. Contact us if you need to use additional ones.