​
Overview

Metadata in Relevance AI helps you extract and organize key information from conversations. These structured data points act as smart labels that make your conversations:

  • Searchable - Find exactly what you need
  • Filterable - Sort conversations by specific criteria
  • Analyzable - Gain insights across multiple interactions

For example, you might add metadata like “customer_segment,” “sentiment_score,” or “product_category” to categorize and later analyze patterns in your conversations.

​
Features

​
Add Metadata

Adding metadata allows you to enrich your data with additional context:

  1. Navigate to the Build tab located at the top of your screen, adjacent to Tasks
  2. Click on “Metadata” in the left sidebar navigation menu
  3. Choose your extraction method (Agent-decided or Rule-based)
  4. Define the appropriate data format and configure your settings
  5. Click the “Save” button to apply your changes

Consider what information would be most valuable for future analysis when deciding which metadata to add. Focus on data points that will help you segment, filter, or understand patterns in your agent interactions.

​
Delete Metadata

To remove metadata that’s no longer needed:

  1. Find the metadata field you want to remove in the Metadata page
  2. Click the delete (trash) icon next to the field

Deleting metadata is permanent and will remove this information from all associated conversations or tasks. Make sure you no longer need this data before proceeding.

​
Edit Metadata Field

To modify an existing metadata field:

  1. Find the metadata field you want to edit in the Metadata page
  2. Click the edit (pencil) icon next to the field
  3. Update the field name, data format, or extraction method as needed
  4. Save your changes

​
Metadata Extraction Methods

Relevance AI offers two approaches for extracting metadata:

​
Let Agent Decide

With this option, you provide instructions to your agent about how and when to extract metadata:

  • How it works: You define guidelines for the agent to follow when determining metadata values
  • Best for: Complex scenarios where context-aware judgment is needed
  • Example: “Extract customer sentiment as ‘positive’, ‘neutral’, or ‘negative’ based on the overall tone of the conversation”

​
Rule Based

This approach uses predefined conditions to automatically extract metadata:

  • How it works: You set specific triggers or patterns that, when detected, will populate metadata fields
  • Best for: Consistent, predictable data points that follow clear patterns
  • Example: If a conversation contains the phrase “interested in pricing,” set lead_status = “pricing inquiry”

​
Data Formats for Metadata

Relevance AI supports various data formats to accommodate different types of information:

  1. Text
    • Free-form text entries
    • Useful for descriptions, notes, or other unstructured information
    • Example: “Customer mentioned competitor Product X”
  2. Number
    • Numerical values for quantitative data
    • Supports integers and decimal values
    • Example: Customer satisfaction score (1-10)
  3. True/False (Boolean)
    • Binary values for yes/no or true/false conditions
    • Example: “is_existing_customer”: true
  4. Single Option
    • Predefined list where only one value can be selected
    • Example: Lead status: [“New”, “Qualified”, “Opportunity”, “Customer”]
  5. Multiple Option
    • Predefined list where multiple values can be selected
    • Example: Products of interest: [“Product A”, “Product B”, “Product C”]

Choose the appropriate data format based on how you plan to use the metadata later. For example, if you want to calculate averages or totals, use the number format. If you need to filter by specific categories, single or multiple option formats work best.

​
Best Practices

  • Be consistent: Use standardized naming conventions and values for your metadata
  • Start small: Begin with a few key metadata fields and expand as needed
  • Review regularly: Periodically assess which metadata fields are providing value
  • Document your schema: Keep track of what each metadata field represents and how it should be used

By effectively utilizing metadata, you can transform raw conversation data into structured, actionable insights that drive better decision-making and agent performance.