Fikri Firman Fadilah3 min read
Cost Attribution in Multi-Tenant GenAI Systems
Practical instrumentation strategies for measuring and allocating LLM costs in production across tenants, A/B tests, and feature flags without sacrificing latency.
← ALL ARTICLES
Topic Filter#observability
Articles tagged with #observability
5 articles in this topic.
Fikri Firman Fadilah5 min read
When Centralized Logging Becomes Your Bottleneck and How to Recover
A field guide to diagnosing log volume problems, choosing between sampling and filtering, and building sustainable logging infrastructure without over-engineering.
Fikri Firman Fadilah4 min read
Designing Systems That Fail Predictably and Safely
Build systems that reduce functionality intentionally rather than cascade. Practical patterns for detecting dependency failures early and maintaining safe operational boundaries.
Fikri Firman Fadilah7 min read
Moving Beyond Benchmark Scores to Production Metrics
Close the gap between offline benchmarks and production reality. Concrete patterns for designing evals that catch hallucinations, detect drift, and drive business decisions.
Fikri Firman Fadilah5 min read
Container Image Bloat in CI/CD Pipelines
How a team's Docker builds hit 45+ minutes and registry storage exploded—and the diagnostic tools and layer-caching strategies that fixed it.