Skip to main content

Automation Concepts

Before building your first automation, it’s important to understand the core concepts that power Agent Studio’s workflow engine.

Nodes (Components)

Nodes are the building blocks of automations. Each node performs a specific function and can be connected to other nodes to create a workflow.

Node Categories

CategoryPurposeExamples
TriggersStart the automation when an event occursAccount Segment, Task Created, Scheduler
ProcessingTransform, filter, or combine dataCreate Data, Update Data, Filter Data
LogicRoute data based on conditionsIf-Else, Condition
ActionsPerform operations like sending notificationsSend Email, Slack Message, Create Task
AIUse LLMs for intelligent processingAgent, LLM, Structured Output

Data Flow

Data flows through your automation from node to node via connections. Each node receives data from its inputs, processes it, and passes results to connected outputs.

The Data Object

All data in Agent Studio flows as Data objects - structured containers with key-value pairs:
{
  "account_id": "acc_123",
  "account_name": "Acme Corp",
  "health_score": 75,
  "renewal_date": "2024-06-15"
}

Accessing Data with @ Notation

When configuring nodes, you can reference values from incoming data using the @ notation:
SyntaxDescriptionExample
@keyAccess a top-level key@account_name → “Acme Corp”
@key.nestedAccess nested values@account.owner.email
@Access the entire data objectFull data dictionary
Example: In an email node, you might set the subject to:
Health Alert: @account_name score dropped to @health_score

Connections

Connections define how data flows between nodes. To connect two nodes:
  1. Click on a node’s output handle (right side)
  2. Drag to another node’s input handle (left side)
  3. Release to create the connection

Connection Rules

  • Every automation must start with exactly one Trigger node
  • Nodes can have multiple inputs and outputs
  • Logic nodes (If-Else, Condition) have separate True and False outputs
  • Actions always execute when reached, even if not connected to downstream nodes

Flow Context

When a trigger fires, it establishes a Flow Context that provides entity information throughout the automation:
Context FieldDescription
account_idThe account associated with the trigger
accountFull account data object
task_idThe task (if applicable)
taskFull task data object
user_idThe user/contact (if applicable)
activity_idThe activity (if applicable)
This context is automatically available to all downstream nodes, allowing you to access related entity data without explicitly passing it.

Execution Model

Node Execution

When a flow runs:
  1. The trigger node executes first, loading entity data
  2. Connected nodes execute in order, following the data flow
  3. Each node processes its inputs and produces outputs
  4. Important: Action nodes always execute their side effects (emails, API calls, etc.) even if their outputs aren’t connected to anything

Conditional Routing

Logic nodes like If-Else and Condition split the flow into multiple paths:
         ┌─── True Path ──→ Send Alert
Condition ─┤
         └─── False Path ─→ Log Only
Only the matching path executes based on the condition evaluation.

Error Handling

If a node fails during execution:
  • The error is logged with details
  • Downstream nodes on that path do not execute
  • Other parallel paths continue normally
  • The flow status reflects the failure

Best Practices

Begin with a basic trigger → action flow. Once working, add processing and logic nodes incrementally.
Use the play button on each node to test it in isolation before running the full flow.
Rename nodes to describe their purpose (e.g., “Check Health Score” instead of “Condition V2”).
Add description fields to complex nodes explaining their purpose and configuration.
Consider what happens with missing data, empty lists, or unexpected values. Use conditions to handle these cases gracefully.

Next Steps

Build Your First Automation

Follow a step-by-step tutorial

Explore Triggers

Learn about available trigger types