Memory

​

Overview

Memory in Relevance AI allows your agent to remember and recall information during and across conversations. There are two types of memory that serve different purposes: These memory systems help make your conversations:

• Searchable - Find exactly what you need
• Filterable - Sort conversations by specific criteria
• Consistent - Ensure the same data is used throughout conversations
• Intuitive - Easily recall and update memorized data when needed

​

Short-Term Memory

Short-Term Memory allows your agent to remember information throughout one conversation. Setup organized memory metadata that your agent can recognize and update as each conversation progresses. This not only can improve the effectiveness of an agent but also can be used to filter, search and analyze tasks. Adding Short-Term Memory allows you to enrich and recall your data with additional context:

1. Navigate to the Build tab located at the top of your screen, adjacent to Tasks
2. Click on “Memory” 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

​

Delete Memory

To remove memory that’s no longer needed:

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

​

Edit Memory Field

To modify an existing memory field:

1. Find the memory field you want to edit in the Memory 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

​

Memory Extraction Methods

Relevance AI offers two approaches for extracting memory metadata:

​

Let Agent Decide

With this option, you provide instructions to your agent about how and when to extract fields from memory. You define guidelines for the agent to follow when determining memory values, making it ideal for complex scenarios where context-aware judgment is needed.

​

Rule Based

Improve memory accuracy by defining specific conditions based on tools & triggers. This approach is either triggered to update after tool run or after trigger received, making it perfect for consistent, predictable data points that follow clear patterns.

​

Data Formats for Short-Term Memory

You can add the following data formats as metadata:

1. Text - Free-form text entries for descriptions, notes, or other unstructured information
2. Number - Numerical values for quantitative data, supporting integers and decimal values
3. True/False - Binary values for yes/no or true/false conditions
4. Single Option - Predefined list where only one value can be selected
5. Multiple Option - Predefined list where multiple values can be selected

​

Built-in Tools

When metadata is added to the Agent, the following built-in tools will be automatically added:

• Add conversation metadata - Allows you to add conversation metadata during agent interactions
• Read conversation metadata - Enables reading existing conversation metadata

This then allows you to add to the Prompt when you want to add conversation metadata, giving you more control over when and how metadata is captured and used.

​

Filtering by Short-Term Memory

You can filter your Workforces and Agent conversations/runs by Short-Term Memory metadata. For example, if you’ve built an agent that uses metadata like an email or user ID for each person, you can filter agent runs by a person’s email or ID to see all their interactions.

​

Best Practices

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

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

---

​

Long-Term Memory

Long-Term Memory allows your agent to remember information across different conversations. This is great for use cases like storing user preferences, frequently asked questions, and other persistent information that should be available in future interactions. When Long-Term Memory is enabled, your agent will be able to read Long-Term Memory added to the agent as it goes.

​

Built-in Tools

Two built-in tools will be automatically added to the agent:

• Save to Memory: Save important information to your Long-Term Memory for future conversations
• Delete from Memory: Remove information from your Long-Term Memory

You can view and manage stored memories from the Memory section of your agent.

​

Advanced Settings

From the Advanced Settings in Long-Term Memory, you can:

• Override the system prompt for saving to memory: Customize how the agent decides what information to save
• Override the system prompt for deleting from memory: Control how the agent determines what to remove from memory
• Disable delete memory tool: When disabled, the agent cannot delete items from Long-Term Memory. This is useful when you want to ensure your agent can’t accidentally lose important context by deleting memories