System Overview
Smartunit agents run inside Node-RED flows and can call configured skills, remember useful facts, track events, and enforce usage budgets. Agent Studio is the monitoring and configuration interface for those agents.
Main Parts
Section titled “Main Parts”| Part | What users use it for |
|---|---|
| Node-RED agent nodes | Build flows that accept messages and produce agent responses. |
| Skills | Let an agent call selected Node-RED flow actions. |
| Memory | Store facts, preferences, summaries, and usage records. |
| Events | Review what happened during a session or turn. |
| Budgets | Stop or warn when a token or spend limit is reached. |
| Agent Studio | Monitor agents, inspect sessions, review memory, and see alerts. |
Runtime Path
Section titled “Runtime Path”The normal message path is:
message -> agent-in -> agent node -> model, skills, memory, and budget checks -> response and event history -> Agent StudioKey Concepts
Section titled “Key Concepts”sessionIdgroups a conversation and its event history.userIdis optional and lets memory follow a user across sessions.- Facts are saved pieces of memory that the agent can reuse later.
- Events are the activity trail shown in Studio.
- Skills are selected flow actions the agent is allowed to call.
- Budgets limit cost or token usage over a configured period.
Safe Operating Notes
Section titled “Safe Operating Notes”Do not place API keys, private customer data, or credentials in docs, screenshots, example prompts, skill descriptions, or public examples. Treat debug logs and event history as potentially sensitive because they may include user messages and model output.