Apr 16 · 21 min read · A note on the code in this article. The observability setup shown here is derived from a production BFF built for a Norwegian enterprise education platform. Resource names, workspace identifiers, aler
Join discussion
Apr 11 · 4 min read · What you'll learn: How to architect a telemetry system that captures agent behavior without slowing down performance The difference between passive metrics collection and active agent instrumentation How to visualize agent decision chains and latenc...
Join discussionMar 11 · 3 min read · You install 16 skills. You see them fire. But here's the question nobody asks: did the model actually follow them? I reviewed every telemetry tool in the Claude Code ecosystem -- built-in OTel, claude_telemetry, claude-code-otel, even the skills.sh p...
Join discussionMar 8 · 10 min read · TL;DR Every time you send a prompt to Claude API, ChatGPT API, Groq, or Cerebras, the provider logs it. Prompts retained for 7-30 days. User IP addresses logged indefinitely. Metadata (timestamps, model used, tokens consumed) stored for compliance au...
Join discussionJan 17 · 6 min read · ⚠️ PERINGATAN PENTING (WAJIB BACA) Panduan ini mengubah sistem secara mendalam (registry, service, scheduled task). Cocok untuk PC kentang / offline / lab / VM. ❗ Risiko: Keamanan menurun drastis (Defender & Update dimatikan). Update fitur & patch ...
Join discussion
