Timeout Mechanisms in Moveo
Moveo uses several timeout mechanisms to manage the lifecycle of conversations. These timeouts serve different purposes and work together to ensure optimal user experience while maintaining system efficiency. This page explains the key timeout mechanisms and how they impact conversations.
Inactivity timeout
The inactivity timeout defines how long the AI Agent
will remember a conversation context before resetting due to user inactivity. If a user sends a message after this timeout period has elapsed, the AI Agent will not remember the previous messages or context.Key features:
- Determines how long conversation history and conversational context (not context variables) are maintained
- Configurable in the AI Agent settings under the Advanced tab
- Available options: 5 min, 15 min, 30 min, 45 min, 1 hour, 2 hours, 8 hours, 24 hours
- Represented as
inactivity_timeout_seconds
in the API (value in seconds)
Use cases:
- Shorter timeouts (5-30 min): Ideal for fast-paced interactions where outdated context should be discarded quickly. This prevents the AI Agent from using stale information that might mislead the conversation.
- Longer timeouts (2-24 hours): Useful for cases where conversations span extended periods. For example, in complex troubleshooting or long-running customer support sessions, a longer timeout allows the AI Agent to maintain context even if the user returns hours later.
How to configure inactivity timeout
- Navigate to your AI Agent
- Click on the Advanced tab
- Choose an option in the Inactivity timeout section
Session timeout
The session timeout is the overall conversation timeout that defines the maximum duration of a conversation. After this period elapses, a new conversation will be created when the user sends a message, regardless of activity.
Key features:
- Varies by channel (e.g., 7 days for WhatsApp, 1 hour for Zendesk)
- Always longer than the
inactivity_timeout
- Represented as
session_timeout
in the API (value in seconds) - Aligned with human agent response timeframes for specific platforms
Behavior:
When a session timeout occurs:
- The current conversation is considered complete
- The session will expire and marked as resolved
- All previous context is cleared, including any collected data or conversation history
Keep alive
The keep alive timeout specifies the number of seconds to keep a session open after it's marked as resolved.
Key features:
- Measured in seconds (e.g., 300 seconds = 5 minutes)
- Represented as
keep_alive
in the API - Applies after a conversation has been explicitly marked as resolved
Use case:
Imagine a customer support scenario where an agent has resolved a user's issue and marked the conversation as complete. With a keep_alive of 5 minutes:
- The conversation remains accessible for 5 minutes after being resolved
- The user can continue the same conversation if they have follow-up questions
- After 5 minutes, a new conversation will be created if the user sends another message
This provides a buffer period for follow-up questions without requiring a completely new conversation to be started.
How to configure keep alive timeout
- Navigate to settings
- Select the environment you want to modify
- Click on Setting tab
- Scroll down to the Keep alive section
Relationship between timeouts
These timeout mechanisms work together to manage conversations efficiently:
- Inactivity timeout: Controls the AI Agent's memory of conversation context
- Session timeout: Sets the absolute maximum duration of a conversation
- Keep alive: Provides a grace period after resolution
In a typical configuration:
- Session Timeout > Inactivity Timeout
- Keep Alive < Inactivity Timeout