AI Field Properties
Overview
Unlock the power of AI to automatically extract the exact information you need from your media content. These new field properties give you precise control over how AI identifies, categorizes, and processes data, ensuring your workflows are efficient and your data is standardized.
Stop manually sifting through audio, video, or text. With these settings, you can guide the AI to pinpoint specific details, classify content accurately, and ensure consistent data capture, saving you time and improving the quality of your insights.
How It Works
These four field properties work together to define how AI extracts data:
Prompt: Your custom instructions to the AI, telling it exactly what information to look for.
Allowed Values: A predefined list of primary or preferred values the AI should extract.
Other Values: A setting that determines if the AI can extract values not on your predefined list.
Not Applicable Values: A fallback response when no relevant data is found.
Getting Started
To access these features, go to Settings → Fields in your dashboard.
Field Properties Explained
Prompt
The Prompt field is your direct instruction to the AI. It tells the AI precisely what data to extract from your media content.
When you create or edit a field, you can define a prompt. This prompt automatically populates when you use the field in an automation, ensuring consistency.
Important Notes:
Changing a prompt in a field definition will NOT update existing automations that use that field.
Prompts work with other field properties (like Allowed Values) for comprehensive extraction rules.
Prompts should be clear, specific, and describe the exact information you want.
Use Cases:
Extract specific entities: "Identify all company names mentioned."
Classify content: "Determine the sentiment of the speaker (positive, negative, neutral)."
Extract structured data: "Find all dates and times mentioned."
Identify topics: "List all product names or services discussed."
Best Practices:
Be specific rather than vague.
Include context about the expected format or type of data.
Reference related field properties in your prompt.
Test prompts with sample content.
Allowed Values
Allowed Values defines a list of primary or preferred values that the AI should extract. This helps standardize your extracted data by limiting the AI to specific options.
This is an array of strings. The AI will try to match content against these values. Its behavior depends on two settings:
1. Selection Mode:
Single Mode: The AI selects only ONE best-matching value.
Multiple Mode: The AI can select one or more applicable values.
2. Other Values Setting:
When Other Values is disabled: The AI MUST ONLY use values from the Allowed Values list (strict mode).
When Other Values is enabled: The Allowed Values become "preferred values," and the AI MAY include other values if they are more accurate.
Output Format:
Single Mode: Returns a single value (e.g., "value1").
Multiple Mode: Returns comma-separated values (e.g., "value1, value2, value3").
Use Cases:
Standardized categories: ["Sales", "Support", "Marketing"]
Status values: ["Active", "Pending", "Completed"]
Priority levels: ["Low", "Medium", "High"]
Best Practices:
Use clear, distinct values.
Order values by priority if applicable.
Keep the list manageable (5-15 values is often ideal).
Use consistent naming conventions.
Other Values
The Other Values setting is a toggle that controls whether the AI can accept values outside your Allowed Values list.
When Other Values is enabled (true):
Allowed Values becomes a "preferred values" list.
The AI can extract values not on the list if they are more accurate or relevant.
This offers flexibility for synonyms or alternative terminology.
When Other Values is disabled (false):
Allowed Values becomes strict and mandatory.
The AI MUST ONLY respond with values from the list.
This ensures complete data standardization.
Use Cases:
Enable to discover new categories or values.
Enable when dealing with synonyms or alternative terms.
Disable for strict data standardization (compliance, reporting).
Disable when working with predefined categories that must not be expanded.
Best Practices:
Enable during initial data collection to discover common values.
Disable once you've identified all common values and added them to Allowed Values.
Consider your data quality requirements: strict standardization vs. flexible discovery.
Review extracted "other" values periodically.
Not Applicable Values
The Not Applicable Values field specifies what the AI should return when no relevant values are found in the content. This provides a consistent fallback response.
When the AI analyzes content and cannot find any matching values (from Allowed Values or relevant data), it will return the value specified here.
Default Behavior:
If Not Applicable Values is not specified or empty, the system defaults to "N/A".
The AI is instructed to return ONLY this value when no match is found.
Use Cases:
Boolean fields: Use "false" or "No" when a condition is not met.
Text fields: Use "Unknown", "Not Specified", or "N/A" when information is missing.
Categorical fields: Use "Uncategorized" or "Other" when no category matches.
Common Values by Field Type:
Field Type | Common Values |
Boolean | "false", "No", "N/A" |
Text | "Unknown", "Not Specified", "N/A", "-" |
Categorical | "Uncategorized", "Other", "None" |
Status | "Not Applicable", "Pending", "Unknown" |
Best Practices:
Choose a value that clearly indicates the absence of data.
Use consistent Not Applicable Values across similar fields.
Consider how these values will appear in reports and filters.
Use values distinct from your Allowed Values.
Field Interactions and Workflow
These four fields work together to create a comprehensive data extraction system:
The Prompt provides the initial instruction on what to extract.
Allowed Values defines the preferred or required values to look for.
Other Values determines flexibility in accepting values outside the list.
Not Applicable Values provides a fallback when nothing matches.
Example Workflow: Call Type Classification
Prompt: "Identify the primary purpose or type of this call from the conversation."
Allowed Values: ["Sales Call", "Support Request", "Product Demo", "Follow-up"]
Allowed Values Mode: Multiple (to allow calls with multiple purposes)
Other Values: Enabled (to catch new call types like "Training" or "Onboarding")
Not Applicable Values: "Uncategorized"
In this scenario:
The AI will look for the four listed call types.
It can also identify and extract other call types if they appear.
If multiple purposes are discussed, it will return a comma-separated list.
If no call type can be determined, it will return "Uncategorized".
Configuration in Automations
When creating or editing automations with Magic Prompt actions:
Field Selection: When you select a field with these properties configured, they auto-populate in the automation.
Override Capability: You can override field-level settings at the automation level for specific use cases.
Field Mapping: The extracted values are automatically mapped to the selected field in your media library.
Consistency: Using field-level prompts ensures consistency, but automation-level overrides allow flexibility.
Troubleshooting
Common Issues and Solutions:
Issue: AI returns values not in the Allowed Values list.
Solution: Disable "Other Values" to enforce strict mode, or add the returned values to your Allowed Values list.
Issue: AI returns "N/A" too frequently.
Solution: Review your prompt for clarity, check if Allowed Values are too restrictive, or verify content actually contains relevant information.
Issue: Multiple values returned when single mode is expected.
Solution: Verify Allowed Values Mode is set to "single" and that your prompt clearly indicates single value extraction.
Issue: Prompt changes not reflected in existing automations.
Solution: This is expected behavior. Update automations manually or create new ones to use updated field prompts.
Next Steps
Ready to get started? Here's what to do next:
Login to your account and navigate to Settings → Fields.
Create a new field or edit an existing one to configure these AI properties.
Experiment with prompts and allowed values to see how they impact data extraction.
Integrate these fields into your automations for seamless data processing.
Need help? Contact our support team or check out our other guides.