{
  "id": 17223,
  "url": "https://www.infoq.com/news/2026/08/pod-deployment-unit-ai-agents",
  "title": "Pods as Workers, Not Agents: Rethinking the Deployment Unit for AI Agents on Kubernetes",
  "summary": "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",
  "authors": "Mark Silvester",
  "category": "news",
  "topics": "agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-06T06:00:00.000Z",
  "fetched_at": "2026-08-07T05:10:58.501Z",
  "source_slug": "x-infoq-ai-ml",
  "source_name": "InfoQ AI/ML",
  "source_homepage": "https://www.infoq.com/ai-ml-data-eng/",
  "ethics_ai_record_url": "https://ethics.ai/record/17223",
  "original_url": "https://www.infoq.com/news/2026/08/pod-deployment-unit-ai-agents",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}