Browse documentation

Workflow node reference

Extract Info

Extract specific information from a message. Exact configuration, outputs, execution behavior, errors, limits, and examples for the Extract Info workflow node.

Automation buildersIntermediateAvailable

What this guide covers

  • Category: AI.
  • Use it to turn unstructured text into named structured fields for later nodes.
  • 2 configuration fields and 2 documented outputs.
  • Extraction does not verify that a claimed value is true.

What this node does

Extract specific information from a message

Use it to turn unstructured text into named structured fields for later nodes.

When not to use it

Do not use it when the data already exists in a reliable structured variable.

Prerequisites

  1. Input text
  2. Explicit field names, types, and descriptions
  3. Validation for required/high-impact values

Inputs and configuration fields

Extract Info configuration fields
FieldKeyControl / typeRequirementDefaultAccepted values and behavior
Message to Extract Frominputvariable-inputRequired when shown{{context.message.content}}Value accepted by the displayed control. Variables supported
Information to ExtractfieldsjsonRequired when shownNo defaultList the pieces of information you want to extract. [ { "name": "email", "description": "Email address" }, { "name": "phone", "description": "Phone number" }, { "name": "date", "description": "Preferred date" } ]

Configure the node

  1. Drag Extract Info from AI in the node palette.
  2. Select the node to open its configuration drawer.
  3. Complete every required field and any conditional field revealed by your choices.
  4. Insert variables only from the current trigger or an earlier node on the same path.
  5. Connect every required output handle to the intended next step.
  6. Save and run Workflow Test with representative data before activation.

Outputs

Later nodes can use these values only after this node has run successfully on the same execution path.

Extract Info output variables
VariableTypeMeaning
{{nodes.ai_extract.extracted}}objectThe extracted information
{{nodes.ai_extract.success}}booleanWhether extraction worked

Execution behavior

  1. Extracts configured fields from input.
  2. Emits an object plus field-level results defined by the node.
  3. Runs for real during Test and may return missing/uncertain values.

Example use case

Extract customer name, company, product, and desired appointment date from an inbound message.

Complete workflow pattern
text
Message Received → Extract Info → Condition → Update Contact → App Action

Common errors

Extract Info common errors
SymptomResolution
A field is missingClarify its definition and handle optional input.
Type is wrongTighten the field type/instructions and validate before use.

Limitations

Extraction does not verify that a claimed value is true.

Do not automatically apply sensitive data without validation.