You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
We recently started receiving the following error whenever users try to message our agent deployed through the new Foundry experience:
"Authorization error encountered when processing your request with activityId=177603228, conversationId=ergsag--gI1@thread.v2. Please ensure that the user with objectId 06fdgagasd03dd8 has Microsoft.CognitiveServices/accounts/AIServices/agents/write action on the project ai_test-resource/ai_proj_test."
Granting the Azure AI User role to affected users resolves the issue and they can interact with the agent again.
However, this introduces a new problem: users with the Azure AI User role are also able to access ai.azure.com and delete the agent directly.
Our intention is for users to interact with the agent (e.g., via Copilot or another interface) without having direct management permissions over the agent resource itself.
Are we misunderstanding the required permission model here, or is there a recommended way to allow users to interact with an agent without granting them permissions that allow them to modify or delete it in Azure AI Foundry?
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
-
We recently started receiving the following error whenever users try to message our agent deployed through the new Foundry experience:
"Authorization error encountered when processing your request with activityId=177603228, conversationId=ergsag--gI1@thread.v2. Please ensure that the user with objectId 06fdgagasd03dd8 has Microsoft.CognitiveServices/accounts/AIServices/agents/write action on the project ai_test-resource/ai_proj_test."
Granting the Azure AI User role to affected users resolves the issue and they can interact with the agent again.
However, this introduces a new problem: users with the Azure AI User role are also able to access ai.azure.com and delete the agent directly.
Our intention is for users to interact with the agent (e.g., via Copilot or another interface) without having direct management permissions over the agent resource itself.
Are we misunderstanding the required permission model here, or is there a recommended way to allow users to interact with an agent without granting them permissions that allow them to modify or delete it in Azure AI Foundry?
Beta Was this translation helpful? Give feedback.
All reactions