InfoQ - AI Architecture

Pods as Workers, Not Agents: Rethinking the Deployment Unit for AI Agents on Kubernetes

Mark Silvester — Thu, 06 Aug 2026 06:00:00 GMT

Running AI agents on Kubernetes raises a key question: should each agent get its own Pod? The kagent project argues no—agents are bursty, short-lived, can spawn subagents, and may wait for human approval, making one Pod per agent wasteful. Agent-substrate adds a control plane to schedule logical “Actors” onto long-lived worker Pods.

By Mark Silvester

Microsoft Agent Framework Harness and Hosted Agents Reach General Availability

Steef-Jan Wiggers — Mon, 03 Aug 2026 10:30:00 GMT

Microsoft's Agent Framework now ships a supported runtime. Build 2026 brought the Agent Harness, the GitHub Copilot and Claude Agent SDK connectors, and the orchestration patterns to stable release; the harness and Foundry Hosted Agents have since reached GA. The shift is from an SDK for building agents to a governed platform for running them.

By Steef-Jan Wiggers

Presentation: Architecting AI Systems for the Messy Reality of Enterprises: Why Agentic Compute is the Missing Layer

Arun Joseph — Mon, 03 Aug 2026 08:08:00 GMT

Arun Joseph shares real-world insights on scaling enterprise agentic platforms like Deutsche Telekom’s LMOS. He discusses bridging organizational fault lines, replacing tool sprawl with core platform abstractions, and moving beyond basic chatbots to operational intelligence systems through ephemeral agents and an Agent Definition Language (ADL).

By Arun Joseph

AWS Launches Amazon GuardDuty Investigation Agent to Automate Threat Triage

Steef-Jan Wiggers — Tue, 28 Jul 2026 07:14:00 GMT

AWS released a public preview of the GuardDuty investigation agent, which correlates findings, 90-day activity logs, and resource topologies into structured reports with risk ratings, confidence scores, and MITRE ATT&CK classification. It is reachable through the AWS MCP Server, so investigations can run from agentic tooling. Preview quotas cap usage at 10 investigations per account per day.

By Steef-Jan Wiggers

Netflix Details its In-House LLM Serving Platform with Triton and vLLM

Matt Foster — Mon, 27 Jul 2026 07:33:00 GMT

Netflix has described the production lessons behind bringing LLM inference into its internal serving platform, including the challenges of supporting different model sizes, hardware requirements, and rapidly evolving inference engines.

By Matt Foster