---
title: "Load balancing AI Assistant | Nutrient"
canonical_url: "https://www.nutrient.io/guides/ai-assistant/deployment/load-balancing/"
md_url: "https://www.nutrient.io/guides/ai-assistant/deployment/load-balancing.md"
last_updated: "2026-06-09T10:25:14.328Z"
description: "AI Assistant requires a single instance deployment. Learn why multiple instances behind a load balancer aren’t supported and how to configure your deployment accordingly."
---

# Load balancing

AI Assistant maintains a persistent connection between the browser and the backend for real-time chat completion and MCP tool calls. This connection must reach the same backend instance throughout a session. Running multiple instances behind a load balancer isn’t currently supported.

## Recommended configuration: Single instance

Run a single AI Assistant instance. This is the supported configuration for all current deployments.

If that instance restarts or is terminated, the WebSocket connection closes, and the AI Assistant user interface (UI) displays a connection error. Users can reload to start a new session. This is expected behavior.

Horizontal scaling of AI Assistant is a known limitation. Multi-instance support is planned for a future release.

---

## Related pages

- [Backup and recovery](/guides/ai-assistant/deployment/backup-and-recovery.md)
- [Selecting the right Docker registry for AI](/guides/ai-assistant/deployment/docker-registry.md)
- [Product activation](/guides/ai-assistant/deployment/product-activation.md)