Skip to main content
Uses an LLM to normalize and transform field values. Ideal for cleaning messy data — standardizing addresses, formatting names, converting units, or restructuring free-text fields.

​
Configuration

SettingDescription
LLM IntegrationThe AI provider to use (e.g., Gemini, OpenAI, Anthropic)
Field MappingsConnect input fields on the left to output fields on the right. Draw lines to define relationships

​
How It Works

1

Define input fields

Select the fields from your data that need normalization (e.g., BillingStreet, BillingCity).
2

Map to output fields

Map each input to a normalized output field (e.g., BillingStreet_Normalized).
3

LLM processes records

The LLM processes each record and writes cleaned values to the output fields.

​
Output

Normalized output fields become available as Mentions in all downstream nodes.

​
Example

Standardize addresses across a Salesforce Account dataset:
  1. Map BillingStreet, BillingCity, BillingState as inputs
  2. Create normalized output fields for each
  3. The LLM cleans formatting inconsistencies (e.g., “123 Main St.” → “123 Main Street”)

​
Best Practices

  • Use specific, descriptive output field names to avoid confusion downstream
  • Test with a small batch first to verify the LLM produces the expected format
  • Choose the right LLM — faster models for simple formatting, stronger models for complex transformations
  • AI Enrichment — uses an LLM prompt to generate new data rather than cleaning existing fields
  • Transform — applies rule-based transformations without an LLM
  • Regex Pattern — extracts or replaces text using regular expressions