The three pillars — logs, metrics, and traces — and making systems understandable.
One agent, one context window, one serial loop — until it stalls at 40 minutes and 180K tokens. The orchestrator pattern fans work out to isolated sub-agents in parallel, then synthesizes. Here's the backend, in compiling Go.
Go 1.26 makes the Green Tea garbage collector the default. What actually changed, how to measure GC CPU before and after on your own workload, and the short window you have to opt out.
Production LLM API patterns: streaming, function calling, retries, token budgets, cost optimization, and observability for backend engineers.
Spring AI 1.1 deep-dive: production RAG pipeline with PII scrubbing, circuit breakers, Micrometer observability, and answer evaluation.
Master observability with real code: Prometheus metrics, structured logging with slog, and OpenTelemetry tracing to debug incidents fast.