Skip to content

Commit 4b110ea

Browse files
committed
bcdr
1 parent e0005cb commit 4b110ea

File tree

1 file changed

+15
-1
lines changed

1 file changed

+15
-1
lines changed

articles/ai-foundry/agents/overview.md

Lines changed: 15 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -7,7 +7,7 @@ author: aahill
77
ms.author: aahi
88
ms.service: azure-ai-agent-service
99
ms.topic: overview
10-
ms.date: 06/25/2025
10+
ms.date: 09/26/2025
1111
ms.custom: azure-ai-agents
1212
---
1313

@@ -116,6 +116,20 @@ Start with the [environment setup](environment-setup.md) and [quickstart](quicks
116116
1. After you create a project, you can deploy a compatible model such as GPT-4o.
117117
1. When you have a deployed model, you can also start making API calls to the service using the SDKs.
118118

119+
## Business Continuity and Disaster Recovery (BCDR) for Agents
120+
121+
To support service resilience, the Azure AI Foundry Agent service relies on customer-provisioned CosmosDB accounts. This ensures that your agent state can be preserved and recovered in the event of a regional outage.
122+
123+
### Use your own CosmosDB account
124+
125+
* As an Azure Standard customer, you provision and manage your own single-tenant CosmosDB account. All agent state is stored in your CosmosDB.
126+
* Backup and recovery rely on CosmosDB’s native capabilities, which you control.
127+
* If the primary region becomes unavailable, the agent will automatically become available in the secondary region by connecting to the same CosmosDB account.
128+
* Since all history is preserved in CosmosDB, the agent can continue operation with minimal disruption.
129+
130+
### Current guidance
131+
132+
We recommend customers provision and maintain their CosmosDB account and ensure appropriate backup and recovery policies are configured. This ensures seamless continuity if the primary region becomes unavailable.
119133

120134
## Next steps
121135

0 commit comments

Comments
 (0)