Live wire — dispatch open22 Oct 2026

The AI Wire

Machine-drafted, human-approved AI industry news. Every story reviewed before it hits the wire.

From the archive68 dispatches · page 02 / 07
75
azure ▸ azure· filed 10 Sept 2026

Azure API Management AI Gateway adds OpenTelemetry observability and cost limit policies

The AI Gateway tier of Azure API Management now emits OpenTelemetry logs, traces, token metrics, and estimated cost metrics, and supports calendar-based cost limit policies that can block requests when projected budgets are reached. The update also refines provider onboarding and expands Anthropic Messages compatibility. Because spend figures are estimates, teams using hard blocks should verify the gap between projections and final billing.

74
azure ▸ tooling· filed 10 Sept 2026

Microsoft Offers MCP Server for Azure Updates With Limited Details

Microsoft has made an MCP server, Microsoft Release Communications, available through the Azure Updates page, describing it as enabling AI-powered discovery of Azure Updates. The listing stops at a link and a purpose statement: it offers no sample queries, data coverage, authentication, or operational details. Engineers can only follow the link to documentation; the feed's query behavior and scope remain unverified.

73
azure ▸ development· filed 6 Sept 2026

Microsoft Foundry details six-phase process for migrating LLM models

Microsoft Foundry has detailed a six-phase process for moving LLM-powered applications between model generations, with model retirement dates now built into the platform lifecycle. The guidance emphasizes that swapping model names can silently change response formatting, schemas, and tool behavior, and that validation and canary rollouts are necessary because offline evaluation can miss production issues. A worked example ends in a deliberate split deployment rather than a clean cutover.

72
simonwillison.net ▸ product· filed 31 Aug 2026

Simon Willison's hands-on test of ChatGPT Work: open internet access, browser automation, and unanswered safety questions

Simon Willison's hands-on test shows ChatGPT Work is an agent platform with unrestricted internet access, a headless Chrome browser, and parallel sub-agents, but OpenAI has not explained how it defends against prompt injection. The documentation is so sparse that he had to ask the agent itself to list its 223 tools and 44 skills. This leaves core safety mechanisms unaddressed in OpenAI's marketing.

69
azure ▸ azure· filed 30 Aug 2026

VNet integration for Azure SRE Agent now generally available

Azure SRE Agent's VNet integration is now generally available, routing agent egress through customer VNets so it can reach private endpoints without public exposure. The feature inherits existing routing, NSG, firewall, and DNS policies, and offers an audit view for policy decisions, though that view is not a complete network audit trail. Setup requires a dedicated empty /27 subnet delegated to Microsoft.App/environments, and switching modes requires disconnecting the VNet first.

65
azure ▸ product· filed 30 Aug 2026

Azure DevOps plugin for GitHub Copilot adds pull request and work item management

Microsoft has released an Azure DevOps plugin for GitHub Copilot that lets developers view and manage assigned pull requests and work items without leaving the Copilot interface. The initial release is limited to opening, editing, and completing work items and pull requests from a "My Work" view, with Microsoft indicating plans to add more capabilities over time. Setup requires signing in and providing organization and project details, but the plugin currently lacks clarity on multi-organization support and real-time updates.

64
azure ▸ product· filed 30 Aug 2026

Microsoft Adds Cost Management Tools to Azure ARM MCP Server

Microsoft has added Cost Management tools to its Azure Resource Management MCP server, enabling AI agents to query cost data, price sheets, and budgets. The default tools cover narrow query and pricing scenarios, while an optional toolset requires opt-in via a header. Deployment involves some configuration friction, and Microsoft says it is expanding these capabilities.

63
azure ▸ product· filed 26 Aug 2026

Live Reports in Azure SRE Agent now in public preview

Microsoft has added Live Reports to its Azure SRE Agent, now in public preview, letting operations teams describe dashboards in natural language and receive a fixed-layout page that refreshes its underlying data on each open. The design separates authoring from rendering, so token costs apply only when reports are created or edited, and optional AI-powered interpretation or action buttons are per-report opt-ins. A four-layer security model restricts network access and validates tool calls against per-version allowlists.

62
azure ▸ tooling· filed 25 Aug 2026

Microsoft Foundry details containerized agent A2A endpoint pattern

Microsoft Foundry now documents how to expose containerized agents as A2A endpoints without reimplementing transport, authentication, or discovery. The design separates control and data plane configurations, requires protocol declarations in both, and cautions against adding application-level A2A routes because the platform handles the A2A transport. Limitations include text-only modality, no streaming, and the necessity of enabling the 'responses' protocol.

61
azure ▸ tooling· filed 25 Aug 2026

Microsoft tutorial: Connecting Foundry AI agents to Dataverse via MCP

Microsoft has published a tutorial for connecting AI agents in Microsoft Foundry to Dataverse using the Model Context Protocol, claiming the integration can be completed in under 30 minutes. The setup requires an Entra ID app registration, specific API permissions, an admin-enabled setting, and careful configuration of OAuth endpoints. However, the process still involves credential management and has potential failure modes such as mismatched URLs and missing admin consent.