Agent¶
The Agent handles requests that need more than a fixed sequence of steps. It uses a connected language model to decide what to do next, can call connected tools, and can use memory to continue a conversation across turns.
Category: Agents
Purpose: Orchestrates an LLM, tools, and memory to solve multi-step tasks.
Inputs:
input- User query or incoming datallm- Language model connection (required)tools- Tool connectionsmemory- Memory connection
Outputs: output - Final response
Configuration:
- Agent Type:
react(reason, act, observe — use with tools),conversational(dialogue focused),task_oriented(single task completion) - User Prompt Template: How the user message is wrapped before reaching the agent. Default
${{input}}— do not remove this placeholder or the user message will never reach the agent - System Prompt: Defines the agent's identity, rules, tone, and limits
- Max Iterations: 1–20, default 5. Caps the reasoning loop. Each iteration is an additional LLM call
- Temperature: 0.0–2.0, default 0.7. Lower values are safer for tool-using agents
- Enable Memory: Default on. Must stay on for a connected memory node to take effect
- Enable Tools: Default on. Must stay on for connected tools to take effect
Usage: Connecting a node is not enough — the matching checkbox must also be enabled.