Skip to main content
The AI Agent node runs a model that decides its own steps at run time. You write instructions in the Message field, wire in tools and triggers, and the agent reasons about the input and acts using the tools you allowed.
AI Agent node on the canvas with input, output, and tool connections

​
Agent or deterministic nodes?

Use regular nodes when the steps are always the same: fetch a row, transform it, post a message. Use an agent when the steps depend on the input, for example triaging messages, deciding which records to update, or doing research that takes a variable number of tool calls. Agents consume credits for model usage unless you connect your own AI subscription. Deterministic integration nodes running on your own credentials cost nothing.

​
The three handles

        (input)  ──▶  ┌──────────┐  ──▶  (output)
   data + triggers    │ AI Agent │       response to
                      └──────────┘       downstream nodes
                           ▲
                        (tools)
            integration nodes, MCP servers,
            filesystem, alarms
HandleDirectionWhat connects there
LeftInputOutput from upstream nodes, and triggers that fire the agent
RightOutputThe agent’s final response, available to downstream nodes
BottomToolsTool providers: integrations, MCP servers, filesystem, alarms
Tool providers connect from their own top handle into the agent’s bottom handle. You can drag these edges yourself, or use the Add trigger and Add tool buttons in the agent’s config panel, which open a searchable palette and handle the wiring for you.
Agent configuration panel with triggers and tools

​
Key settings

FieldWhat it does
System PromptInstructions defining how the agent behaves
MessageThe task or question. When a trigger is wired in, the fired event is delivered alongside this message, so write standing instructions here, not the event itself
TemperatureCreativity level, 0.0 (focused) to 2.0 (creative)
Conversation KeySame key = same conversation across runs. See Conversations
Show in InterfaceSurfaces the agent as a fullscreen chat in the workflow’s Interface tab

​
Next steps

Models and harnesses

Choose between the built-in LLM agent and five CLI coding agents, or connect your Claude or ChatGPT subscription.

Tools from integrations

Turn any integration node into a set of agent tools with an operation allowlist.

Channel agents

Build chat-style agents on Slack, Telegram, WhatsApp, or email.

Conversations

Keep context across runs with conversation keys.