Documentation Index Fetch the complete documentation index at: https://docs.duckie.ai/llms.txt
Use this file to discover all available pages before exploring further.
This page provides a complete reference for all node types and condition options available in workflows.
Node Types Start Node The Start node is the entry point for the workflow. Duckie creates it automatically when you create a workflow.
Outputs:
Next — Begins workflow execution
Executes a tool or another reusable resource.
Configuration: Field Description Name Display name for this node Tool The Duckie tool, app tool, custom tool, MCP tool, runbook, or workflow to execute Inputs Values mapped to the selected tool’s parameters Outputs Values produced by the tool for later nodes
Outputs:
Success — Tool executed successfullyFailure — Tool execution failed
Example uses:
Search company docs
Send a response with the Responder tool
Call a custom API
Call a tool from an MCP server
Run a runbook or another workflow
Create a Jira ticket or update a Zendesk ticket
Decision Node Routes the workflow across branches. Branches are evaluated from top to bottom. The first matching branch is taken; if no branch matches, the Else path is taken.
Configuration: Field Description Name Display name for this node Branches Ordered rule or AI conditions Else Fallback path when no branch matches
Outputs:
One output per branch
Else fallback output
End Node Marks a workflow path as complete.
Condition Reference Decision branches can use a Rule condition or an AI condition.
Rule Conditions Rule conditions compare a selected value against another value.
Field Description Check The value to evaluate Condition The comparison to apply Value The value to compare against, when the comparison needs one
Available comparisons:
Comparison Use for equals Exact matches does not equal Excluding a value is greater than Numeric comparisons is less than Numeric comparisons is at least Numeric lower bounds is at most Numeric upper bounds contains Text or list membership does not contain Excluding text or list membership starts with Prefix checks ends with Suffix checks is empty Missing or null values is not empty Present values is true Boolean true is false Boolean false
AI Conditions AI conditions use a prompt and selected inputs to make a judgment.
Field Description Mode Basic or Advanced reasoning Prompt The decision the AI should make Inputs Context the AI should evaluate
Example prompt:
Determine whether the customer is satisfied with the resolution. Consider their latest message, conversation history, and whether the original issue appears resolved.
Use input mapping to pass values into tool parameters and conditions.
Source Use for Manual Value Fixed strings, numbers, booleans, or JSON Ticket Data Metadata from the conversation or source ticket Previous Node Outputs from earlier workflow nodes Saved Value Values saved for reuse in the workflow Generate with AI Values generated from selected context Multiple Items Lists of values for parameters that accept arrays
Best Practices Node Naming
Use descriptive names: “Check order eligibility” not “Decision 1”
Include the action: “Lookup order in database”
Be consistent across workflows
Error Handling
Always connect Failure outputs
Provide fallback paths for errors
Consider retry logic for transient failures
Testing
Test each path through the workflow
Verify variable mapping works correctly
Check edge cases and error conditions
Next Steps
Create Workflows Build workflows using these nodes
Tools Reference See available tools for Tool nodes
