A fully managed platform in Microsoft Foundry for hosting, scaling, and securing AI agents built with any supported framework or model
Foundry: Missing Connected Resource Keys Causing Authentication Failures
Microsoft's poor support AI is worse than Copilot ... but support request is stuck. My problem is the Foundry agents broke overnight AEST, unusable. Agents page doesn't even load. Models and portal still work. Connected Resources all show "No key…
Foundry Agent Service
How can we disable prompt and response content in Foundry "responsesapi" traces while keeping operational telemetry?
We have a .NET Microsoft Agent Framework hosted agent deployed to Microsoft Foundry. The Foundry project is connected to Application Insights. We want to retain operational telemetry, such as latency, errors and token usage, but avoid recording user…
Foundry Agent Service
A fully managed platform in Microsoft Foundry for hosting, scaling, and securing AI agents built with any supported framework or model
Foundry conversations return 404 after ~60 days even though we never deleted them. Is there automatic expiration?
Hi all. We run a production chatbot on the Foundry project endpoint (conversations + responses). We only delete a conversation when the user deletes the chat, but lately a lot of old conversations started returning 404 on GET…
Foundry Agent Service
A fully managed platform in Microsoft Foundry for hosting, scaling, and securing AI agents built with any supported framework or model
AI answer
Microsoft Foundry: Agent Creation Failing with HTTP 404 in East US 2
Problem description I am unable to create agents in my Azure AI Foundry project located in the East US 2 region. All attempts to create new agents, including minimal prompt-only agents with no tools, result in an HTTP 404 not_found error, stating that a…
Foundry Agent Service
A fully managed platform in Microsoft Foundry for hosting, scaling, and securing AI agents built with any supported framework or model
Networking: DNS delay in VNet-injected hosted agent after sandbox start — Behavior and troubleshooting
Problem description I am experiencing a delay of 5 to 13 seconds after each sandbox start where my private DNS path (UDP to hub firewall) is unavailable, while public TCP connectivity works immediately. This affects the initial DNS queries from each new…
Foundry Agent Service
A fully managed platform in Microsoft Foundry for hosting, scaling, and securing AI agents built with any supported framework or model
Foundry-to-Foundry A2A: child agent writes a SendMessage payload as text instead of calling its configured agent
I'm testing a small native hierarchy of prompt agents in Microsoft Foundry: a coordinator calls two managers, and one manager should delegate to another agent through A2A. The coordinator, using gpt-4.1-mini, successfully invoked both managers. The…
Foundry Agent Service
A fully managed platform in Microsoft Foundry for hosting, scaling, and securing AI agents built with any supported framework or model
Foundry Agent Service: creating agent versions returns 404 “resource referenced… not found” in one project only; a new project in the same account works
Problem Since 27-Oct-2026, every agent create in one Foundry project fails, from the portal, the SDK and REST: POST {project-endpoint}/agents/{name}/versions?api-version=v1 404…
Foundry Agent Service
A fully managed platform in Microsoft Foundry for hosting, scaling, and securing AI agents built with any supported framework or model
AI Foundry Hosted Agent A2A stopped working HOSTED_AGENT_NOT_SUPPORTED
We have encountered an issue with incoming A2A (Agent-to-Agent) requests to Microsoft Foundry Hosted Agents that previously worked successfully. Our Hosted Agent was successfully receiving A2A message/send requests through September 21, 2026, as…
Foundry Agent Service
A fully managed platform in Microsoft Foundry for hosting, scaling, and securing AI agents built with any supported framework or model
Microsoft 365: Publishing Autopilot Agent Fails with 502 Upstream Dependency Error
Problem description *Note: I've posted the same question also earlier, but Microsoft support demands that I post it from the ticket again to proceed. The previous post, which did not yield a solution:…
Foundry Agent Service
A fully managed platform in Microsoft Foundry for hosting, scaling, and securing AI agents built with any supported framework or model
Azure AI Search Private Endpoint Connection Issue — HTTP 424 Tool Server Error
Setup (production, Japan East): Microsoft Foundry account with public network access disabled + private endpoint, standard agent setup with virtual network injection into a delegated subnet, project-level capability host with bring-your-own Azure AI…
Foundry Agent Service
A fully managed platform in Microsoft Foundry for hosting, scaling, and securing AI agents built with any supported framework or model
Azure AI Foundry Agent Works in Studio but Fails When Deployed to Microsoft Teams
I developed an agent in Microsoft Foundry that uses Logic Apps MCP tools to query and update data in a database. The agent works correctly in Foundry Studio, but after publishing to Microsoft Teams, it times out and fails with any prompt. Observed…
Foundry Agent Service
A fully managed platform in Microsoft Foundry for hosting, scaling, and securing AI agents built with any supported framework or model
AI answer
Secure enterprise tool calling
How can an Azure-hosted AI agent securely invoke enterprise APIs, databases, and Microsoft Graph operations using managed identities and least-privilege access? What controls should be implemented to prevent prompt injection from causing unauthorized…
Foundry Agent Service
A fully managed platform in Microsoft Foundry for hosting, scaling, and securing AI agents built with any supported framework or model
Microsoft Foundry: hello-world autopilot microsoft365/publish returns 502 upstream_dependency_failed
Publishing the official hello-world autopilot sample to Microsoft 365, samples/python/autopilot-agents/hello-world seems to fail – any idea of what to look at? What happens: azd deploy succeeds. Publishing then fails. azd ai agent publish stops…
Foundry Agent Service
A fully managed platform in Microsoft Foundry for hosting, scaling, and securing AI agents built with any supported framework or model
Foundry Agent Service: MCP tool result with isError ends the whole response (tool_user_error) on the new Responses API
Summary In the new Foundry Agent Service (Responses API with agent_reference), a remote MCP tool call whose result has isError: true ends the entire response with tool_user_error. The model never sees the tool error, so it cannot correct its call or…
Foundry Agent Service
A fully managed platform in Microsoft Foundry for hosting, scaling, and securing AI agents built with any supported framework or model
Foundry IQ Knowledge Base incorrectly detected as OBO with API Key
Our Foundry agent works correctly in the Playground and also works from our application with API Key when no Knowledge Base is attached. When a Foundry IQ Knowledge Base is attached, the same API Key call fails with: Tools configured with OBO auth are…
Foundry Agent Service
A fully managed platform in Microsoft Foundry for hosting, scaling, and securing AI agents built with any supported framework or model
Open AI Decisions API availability Inquiry
When will this newly released OpenAI Decisions API be available in foundry?
Foundry Agent Service
A fully managed platform in Microsoft Foundry for hosting, scaling, and securing AI agents built with any supported framework or model
New Azure AI Foundry Search Service DNS issues with Network Isolation and Private Endpoints.
We have been using Azure AI foundry for a couple years now and have not had any issues with connectivity to our resources like search service that are setup to use private endpoint. Now that we are trying to create an agent in the new foundry…
Foundry Agent Service
A fully managed platform in Microsoft Foundry for hosting, scaling, and securing AI agents built with any supported framework or model
AI answer
Intermittent failure when invoking MCP tools through A2A in Microsoft Foundry
Currently evaluating an Agent-to-Agent (A2A) integration pattern in Microsoft Foundry involving multiple agents and MCP-based tool integrations. The setup consists of two Foundry agents: One agent connected to ROVO MCP for Jira-related operations A…
Foundry Agent Service
A fully managed platform in Microsoft Foundry for hosting, scaling, and securing AI agents built with any supported framework or model
How to connect to Azure Foundry Playground and Agent via Private Endpoint
My environment is configured as follows: A virtual machine (VM) located in the corporate network (A) An Azure Foundry resource created in the East US 2 region. I have also created a Private Endpoint in the Southeast Asia region (B) The VM (A) is…
Foundry Agent Service
A fully managed platform in Microsoft Foundry for hosting, scaling, and securing AI agents built with any supported framework or model
Microsoft Foundry: Agent Stopped Working — Cannot Invoke Connected Agent
Problem description I am experiencing an issue where my Foundry agent has stopped working. Specifically, I cannot invoke the connected agent, and attempts to start a new chat in the Azure AI Foundry Playground result in an InternalServerError with the…
Foundry Agent Service
A fully managed platform in Microsoft Foundry for hosting, scaling, and securing AI agents built with any supported framework or model