Category: AI-Ops

August 23, 2026 · Weekly Edition AI Ops The bill arrived. Gartner now expects agentic AI inference costs to rise more than fivefold by the end of 2028 even as per-token prices keep falling, and most of this week’s coverage is a set of answers to that arithmetic: Snowflake auto-routing…

August 16, 2026 · Weekly Edition AI Ops Inference economics is the story of the week. Nvidia ships a router that picks a cheaper model per request, Alibaba Cloud uses a two-lane agent to avoid calling an LLM at all, open weights keep dragging the serving price floor down, and…

August 9, 2026 · Weekly Edition AI Ops Weekly Running the app-and-infra stack with AI — and running AI itself in production. This week: agent orchestration and agent observability both get real evaluation criteria, agents start doing unglamorous production work (data plumbing, incident triage), and a fresh round of inference-infrastructure…