Skip to main content

​
Overview

The Validator step acts as a quality gate in your workflow. It takes the output from previous steps and checks it against validation rules you describe in natural language. The AI evaluates each rule and returns a boolean valid result plus an array of specific error messages for any rules that failed. This is useful when you need to:
  • Verify required fields are present before writing to a database
  • Check that API response data meets expected formats or ranges
  • Enforce business rules (e.g. “royalty rate must be between 0 and 1”)
  • Catch bad data early before it flows to downstream steps

​
How It Works

At runtime, the Validator receives the full execution context as input. Your prompt defines the rules to check. The AI returns a structured result with valid (true/false) and errors (an array of human-readable error strings). When valid is false, you can use branches to route the workflow to an error-handling path.
Prompt:
Validate the contract data:
- "title" must be a non-empty string
- "effective_date" must be a valid date in YYYY-MM-DD format
- "royalty_rate" must be a number between 0 and 1
- "parties" must be an array with at least 2 entries
Output when valid:
{
  "valid": true,
  "errors": []
}
Output when invalid:
{
  "valid": false,
  "errors": [
    "royalty_rate is 1.5, which exceeds the maximum of 1",
    "parties has only 1 entry, minimum is 2"
  ]
}

​
Configuration

FieldDescription
PromptNatural language validation rules to check against the input data. Use template variables to reference specific data from previous steps.

​
Writing Good Prompts

  • List rules explicitly — each rule on its own line makes it easier for the AI to evaluate and report individually
  • Include expected types and ranges — “must be a number between 0 and 100” is better than “must be reasonable”
  • Be specific about what counts as failure — e.g. “empty strings and null values should fail the non-empty check”

​
Using Libraries

The prompt editor has built-in library integration. Click Library above the editor to load a saved prompt, or click Save to store the current prompt as a reusable library item. This is useful when the same validation rules apply across multiple automations.

​
Output

FieldTypeDescription
validbooleanWhether all validation rules passed
errorsarrayList of human-readable error messages for failed rules (empty when valid)
errorbooleanWhether a system error occurred
error_messagestringError description if the step itself failed
Combine with branches to create conditional paths: add a branch on output.valid equals false to route to error handling, and let the default connector continue the happy path.