Howie Leung (howieleung) · Nov 6, 2026 · Nov 7, 2026
@@ -4,6 +4,7 @@
 
 ### Features Added
 
+* Agent Insights monitor APIs are now GA, available through `.agent_insight_monitors` without a preview opt-in header. Custom run pollers continue to expose the run ID through `details`.
 * Added preview `.beta.voice_agents.live.connect()` and `VoiceAgentLiveDefinition` for synchronous and asynchronous GPT Live sessions, with typed client and server events, session updates, text and audio input, and Responses backend function-tool support.
 * Added Live delegation models for Responses backends, application-managed work, and same-project prompt agents: `VoiceAgentLiveResponsesDelegation`, `VoiceAgentLiveClientDelegation`, and `VoiceAgentLiveManagedAgentDelegation`.
 * Added `.beta.voice_agents.live_conversations` for listing, retrieving, and deleting stored Live conversations, retrieving conversation items, and retrieving or downloading item-level and conversation-level audio.
@@ -27,12 +28,16 @@ All breaking changes affect preview APIs.
 
 Breaking changes in beta methods:
 
+* Moved `.beta.agent_insight_monitors` operations to the top-level `.agent_insight_monitors` sub-client.
+* Agent Insights monitor `create()`, `update()`, `begin_create_run()`, and `update_insight()` now accept keyword parameters or JSON/binary bodies instead of dedicated preview request models. Use `lookback_hours` for run inputs.
 * Argument `telephony_binding` in `.beta.voice_agents.telephony.create_binding()` renamed to `binding`; the typed body now accepts `TelephonyBinding` instead of `CreateTelephonyBindingRequest`.
 * Argument `body` in `.beta.voice_agents.telephony.create_call_job()` renamed to `job`; the typed body now accepts `TelephonyCallJobCreate` instead of `CreateTelephonyCallJobRequest`.
 * Removed the `status` filter from `.beta.voice_agents.telephony.list_bindings()`.
 
 Breaking changes in beta classes:
 
+* Class `BetaAgentInsightMonitorsOperations` renamed to `AgentInsightMonitorsOperations`.
+* Removed `AgentInsightMonitorCreate`, `AgentInsightMonitorUpdate`, `AgentInsightRunCreate`, and `AgentInsightUpdate`; use the corresponding operation's keyword parameters instead.
 * Removed `CreateTelephonyBindingRequest`, `CreateTeamsPhoneExtensibilityTelephonyBindingRequest`, and `CreateTwilioTelephonyBindingRequest`. Use `TelephonyBinding`, `TeamsPhoneExtensibilityTelephonyBinding`, and `TwilioTelephonyBinding`, respectively.
 * Class `CreateTelephonyCallJobRequest` renamed to `TelephonyCallJobCreate`.
 * Removed `TelephonyOutboundDestination` and `TelephonyOutboundDestinationType`; use `TelephonyAddress` and `TelephonyAddressType`. The `source` and `destination` properties on `TelephonyCallJobCreate` and `TelephonyCallJob` now use `TelephonyAddress`; `source` no longer accepts a plain string.
@@ -50,6 +55,7 @@ Breaking changes in beta classes:
 
 ### Sample updates
 
+* Agent Insights samples demonstrate GA analysis priorities, instructions, and plural status filters.
 * Added Live voice-agent samples under `samples/agents/voice/` for session lifecycle, text and audio conversations, local function tools, and same-project managed-agent delegation.
 * Added `sample_voice_agent_live_read_conversation.py` demonstrating stored Live conversation, transcript, and audio retrieval, with an optional temporary greeting session.
 * Added `sample_voice_agent_read_generated_audio.py` demonstrating retrieval of generated, unheard audio from an interrupted Realtime reply.

@@ -35,6 +35,7 @@ resources in your [Microsoft Foundry](https://ai.azure.com/) Project. Use it to:
 * **Enumerate connected Azure resources** in your Foundry project using `.connections` operations.
 * **Upload documents and create Datasets** to reference them using `.datasets` operations.
 * **Create and enumerate Search Indexes** using `.indexes` operations.
+* **Analyze agent traces and manage insights** with configurable priorities, on-demand runs, scheduled monitors, and list-based insight filters through `.agent_insight_monitors` operations.
 * **Explore additional evaluation tools (some in preview)** to assess the performance of your generative AI application, using `.evaluation_rules`,
 `.beta.evaluation_taxonomies`, `.beta.evaluators`, `.beta.insights`, and `.beta.schedules` operations.
 * **Manage memory stores (preview)** for Agent conversations, using `.beta.memory_stores` operations.
@@ -175,7 +176,7 @@ The table below lists the operation groups supported by the client library, with
 | Topic | Foundry documentation | Samples folder |
 |---|---|---|
 | Agents (create, run, stream) | [Agents overview](https://learn.microsoft.com/azure/foundry/agents/overview) | `samples/agents/` |
-| Agent Insights (preview) | | [On-demand analysis and scheduled monitors](https://github.com/Azure/azure-sdk-for-python/tree/main/sdk/ai/azure-ai-projects/samples/agent_insights) |
+| Agent Insights | | [On-demand analysis and scheduled monitors](https://github.com/Azure/azure-sdk-for-python/tree/main/sdk/ai/azure-ai-projects/samples/agent_insights) |
 | Hosted agents | [Hosted agents concepts](https://learn.microsoft.com/azure/foundry/agents/concepts/hosted-agents), [Deploy your first hosted agent](https://learn.microsoft.com/azure/foundry/agents/quickstarts/quickstart-hosted-agent) | `samples/hosted_agents/` |
 | Agents tools | [Tool catalog](https://learn.microsoft.com/azure/foundry/agents/concepts/tool-catalog) | `samples/agents/tools/` |
 | Agents optimization | [Prompt optimizer](https://learn.microsoft.com/azure/foundry/observability/how-to/prompt-optimizer), [Agent optimizer overview](https://learn.microsoft.com/azure/foundry/agents/concepts/agent-optimizer-overview) | `samples/agents/optimization/` |