Start Node — Settings
The Start node defines how a workflow begins and how incoming user messages are handled before reaching other nodes.
This node controls message storage behavior, safety guardrails, and error-handling preferences.
This document explains what each setting does conceptually, without describing internal logic or implementation.
Store in Chat
Purpose
Controls whether user messages that trigger the workflow are stored in chat history.
Behavior
- When enabled, user input and workflow responses are saved and visible in chat conversations.
- When disabled, interactions are processed but not stored for future reference.
Use Case
- Enable for support, sales, or audit-friendly workflows.
- Disable for sensitive or ephemeral interactions.
Guardrails
Guardrails help ensure safe, compliant, and controlled user interactions.
Each guardrail can be enabled independently and configured through its own settings modal.
PII (Personally Identifiable Information)
Purpose
Detects and manages sensitive personal information in user input.
PII Detection Settings
Contact Information
- Email Address
- Phone Number
- Person Name
- Location
- Date & Time
- URL
Financial Information
- Credit Card Number
- Bank Account Number
- International Bank Account Numbers (IBAN)
- Crypto Wallet Address
Government IDs (USA)
- US Social Security Number
- US Passport Number
- US Driver License
- US Individual Taxpayer Identification Number (ITIN)
Government IDs (International)
- UK National Insurance Number
- Canada Social Insurance Number
- India Aadhaar Number
- Singapore National Registration Identity Card (NRIC)
Medical Information
- Medical License
Device Identifiers
- IP Address
- MAC Address
Australia-Specific Identifiers
- Australian Business Number (ABN)
- Australian Company Number (ACN)
- Tax File Number (TFN)
- Medicare Number
Address Information
- US Address
- Canadian Address
Action
Defines how detected PII is handled.
- Mask
Replaces detected PII with masked characters before processing or storing the message, preventing sensitive information from being exposed while keeping the rest of the content intact. - Block
Prevents the message from being processed if PII is detected. The workflow stops and the user is notified that sensitive information cannot be accepted. - Skip Storage
Allows the message to be processed normally, but excludes the detected PII from being saved in chat history or logs.
Confidence Threshold
Default: 50%
Controls how confident the system must be before treating detected content as PII.
- Higher value → stricter detection
- Lower value → more permissive detection
Custom Patterns
Allows adding custom patterns for identifying sensitive data.
Actions
- Add – Save the custom pattern
- Cancel – Discard changes
Moderation
Purpose
Filters user input based on content categories to prevent unsafe or harmful conversations.
Content Categories
- Sexual
- Sexual / Minors
- Hate
- Harassment
- Harassment / Threatening
- Violence
Confidence Threshold
Defines the minimum confidence required to trigger moderation.
Jailbreak
Purpose
Prevents users from attempting to bypass system rules or manipulate assistant behavior.
Behavior
- Blocks or restricts prompts intended to override instructions or safeguards.
Custom Prompt Check
Purpose
Applies custom rules to validate user input against a defined system prompt.
Settings
- System Prompt
A custom instruction used to evaluate user input. - Confidence Threshold
Determines sensitivity for triggering this check.
NSFW Filter
Purpose
Detects and restricts not-safe-for-work content.
NSFW Categories
- Nudity
- Suggestive Content
- Explicit Content
Confidence Threshold
Controls detection strictness for NSFW content.
Continue on Error
Purpose
Controls workflow behavior when an error occurs in the Start node.
Behavior
- When enabled, the workflow continues even if an error is encountered.
- When disabled, the workflow stops on error.
Use Case
- Enable for resilient flows where partial execution is acceptable.
- Disable when strict validation is required.
Summary
The Start Node Settings allow you to:
- Control message storage
- Apply safety and compliance guardrails
- Detect and handle sensitive information
- Filter harmful or unsafe content
- Define error-handling behavior
These settings ensure that workflows start in a controlled, secure, and compliant manner before proceeding to other nodes.