What These Are: The building blocks of your workflows. Each node type does a specific job in your automation pipeline.Important: You configure these visually in Agent Studio - the JSON examples below are just to show you what gets generated.
What It Does: Defines what data your workflow needs to run (like function parameters).When You Use It: Every workflow needs this to define what data comes in.Example Use Cases: Customer message, file upload, user preferences, priority level
Copy
Ask AI
{ "name": "user_input", "function": "inputs", "params": { "keys": { "customer_message": "string", // What the customer wrote "priority": "string", // urgent, normal, low "customer_email": "string" // For follow-up } }}
How to Configure: In Agent Studio, drag an “Input” node, then define each input field you need.
What It Does: Sends data to your AI agent for processing (analysis, generation, decision-making).When You Use It: When you need AI to understand, analyze, or generate content from your data.Example Use Cases: Sentiment analysis, content generation, data extraction, classification
Copy
Ask AI
{ "name": "ai_processor", "function": "agent", "params": { "config": { "agent_id": "your_agent_id", // Which AI agent to use "api_key": "your_agent_key" // Authentication }, "query": {"depends": "user_input"} // Gets data from input node }}
How to Configure: In Agent Studio, drag “Agent” node, select your AI agent, it automatically connects to previous nodes.What You Get Back: AI agent’s response/analysis that you can use in subsequent nodes.
What It Does: Calls your existing systems (CRM, databases, notification services, etc.).When You Use It: When you need to update external systems or get data from them.Example Use Cases: Update Salesforce, send Slack notifications, query databases, call webhooks
How to Configure: In Agent Studio, drag “API” node, enter URL and method, map data from previous nodes.Enterprise Power: This is how you integrate workflows with ALL your existing systems.
What It Does: Uses AI to make decisions about where the workflow should go next.When You Use It: When you need intelligent branching based on content, not just simple if/then rules.Example Use Cases: Route based on sentiment, escalate high-priority issues, approve/reject based on AI analysis
Copy
Ask AI
{ "name": "quality_check", "function": "gpt_conditional", "params": { "openai_api_key": "sk-...", "condition": "confidence > 0.8", // AI evaluates this condition "context": {"depends": "ai_processor"}, // Data for AI to analyze "true": "auto_approve", // Node to go to if true "false": "human_review" // Node to go to if false }}
How to Configure: In Agent Studio, drag “Conditional” node, set your condition, connect true/false paths to different nodes.Why This Is Powerful: AI makes nuanced decisions that simple if/then rules can’t handle.