The Pulse of LLMOps, FinOps
& AI Infrastructure
Intelligence for engineers building and operating AI infrastructure at scale. LLMOps, FinOps, Kubernetes, and the tools that keep production AI running.
Deep Technical Guides
Benchmarks run on real infrastructure. Config files you can copy-paste. No vendor fluff.
Cost Optimization Playbooks
Datadog to Grafana migrations. GPU budget triage. Reserved instance strategy. Real savings.
Production Incident Frameworks
Postmortem templates for AI failures. Runbooks your on-call team will actually use.
Latest Articles
View all →Mesh Inference on iroh: GPUs in Three Offices and a Closet
Mesh LLM turns scattered GPUs into one OpenAI-compatible API. Skippy split-mode layer-pipeline inference behind localhost:9337/v1 — and the OTel gap.
OpenAI Just Made Your Agent a Black Box (and What to Do)
Codex multi-agent-v2 encrypts the parent→subagent payload. The agent-side OTel proxy that keeps your plaintext copy before Responses encrypts it
Custom AI Silicon 2026: Meta MTIA, Trainium2, TPU, Maia
Meta MTIA 300/450/Iris, AWS Trainium2/Inferentia2, Google TPU v5e/v6, Microsoft Maia 100 vs NVIDIA H100/B100 — vendor-neutral, dollar-per-token.
Per-Engineer AI Observability 2026: Beat Reflection
OTel + LangSmith + ClickHouse reference schema for per-engineer Claude observability — session cost, four-signal dashboard, 1/3/6/12-month retention.
Agent Observability at 1,200+ Agents: OTel Stack 2026
AWS AgentCore vs. OSS for 1,200-agent fleets: OpenTelemetry gen_ai.* conventions and a Tempo / ClickHouse / OpenSearch trace-store comparison.
Agent Sandbox vs. Agent Substrate: CNCF Runtime 2026
Two CNCF SIG Apps projects — agent-sandbox and agent-substrate — and the OTel pattern that makes both debuggable in production.
Stay ahead of the stack.
Weekly intelligence on LLMOps, FinOps, and AI infrastructure. No fluff, no vendor pitches. Written by practitioners, for practitioners.