The AI Wire

azure ▸ product· filed 30 Aug 2026

Cohere Parse Document Extraction Model Now Available in Microsoft Foundry

Cohere Parse, a vision language model for extracting structured data from documents, is now available in Microsoft Foundry on Azure, converting tables, forms, and embedded images into Markdown while keeping inference within the customer's tenant. The model returns bounding boxes for downstream citation and reports throughput of 4.5 pages per second per GPU at $1.50 per thousand pages. Its domain-focused training on finance, insurance, scientific research, and nine languages means teams with other document types should validate output on their own corpus.

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.

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.

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.

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.

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.

azure ▸ azure· filed 25 Aug 2026

The Hardest Problems in Shipping AI Agents Are Operational, Not Architectural

The primary challenges in deploying AI agents to production are operational, not architectural: grounding quality, tool reliability, observability, and security cause most failures. Reliability, not intelligence, determines production readiness, and practical advice includes designing for tool failure, enabling tracing, and planning cost optimization from day one. A ten-point readiness checklist is offered, but its sufficiency remains unresolved.

youtube.com ▸ tooling· filed 24 Aug 2026

herdr: An 11-Megabyte Terminal Utility That's Ready in Under a Second

herdr is an 11-megabyte terminal utility that installs in under a second via a single curl command. Despite initial skepticism from a terminal-focused YouTuber who had previously dismissed other tools, the reviewer found herdr's simplicity appealing and now uses it daily on a home lab server. The article suggests that the utility's low-friction setup complements its practical value.

youtube.com ▸ industry· filed 23 Aug 2026

The Expanding Scope of Forward Deployed Engineering and Its Ties to Outcome-Based Pricing

Natalie Mier, head of agent engineering at Sierra, argued in a recent talk that forward deployed engineering has accumulated responsibilities across four phases—DevOps, data integration, custom solution building, and enablement—so that it now means something different at nearly every company. She contends that with AI agents lowering the cost of code, the role's core accountability to customers is converging with product engineering, and that outcome-based pricing models make this generalist role more central. Mier also noted that the term may lack a coherent definition, but someone still must be accountable for whether software works for the customer.

developer.nvidia.com ▸ research· filed 22 Aug 2026

AVO agent architecture achieves perfect ARC-AGI-3 score and produces optimized GPU kernels

The AVO agent architecture, designed for long-running autonomous work, achieved a perfect score on the ARC-AGI-3 public set and produced GPU kernels that outperformed existing libraries. The system uses persistent memory and a supervisor to sustain progress. Results show fewer environment actions than a comparable harness, but limitations include public-set-only evaluation and unqualified cross-model comparisons.