https://reops.tech/blog/ ReOps Tech Blog Articles on running AI in production, AgentOps, AI platform governance, and regulated cloud infrastructure - plus the DevOps foundations underneath. 2026-07-15T00:00:00Z Bogdan Moldovan https://reops.tech/portfolio/ https://reops.tech/favicon.png https://reops.tech/assets/img/logo.png https://reops.tech/blog/operating-agentic-systems-in-production/ Operating Agentic Systems in Production: Lessons from Building Tendwell 2026-06-03T00:00:00Z 2026-06-03T00:00:00Z Lessons from building Tendwell, a local-first AgentOps tool: deterministic SLO evaluation, propose-versus-execute separation, and a tamper-evident audit log. https://reops.tech/blog/dora-article-17-incident-classification/ The four-hour clock starts before you understand the incident: notes on DORA Article 17 in practice 2026-05-14T00:00:00Z 2026-05-14T00:00:00Z Field notes on DORA Article 17 — why incident classification is harder than it looks, and why the tooling you bring in is itself a compliance surface. https://reops.tech/blog/bobys-garage-journey/ Boby's Garage: From a Colab Notebook to a Two-Engine On-Device Car Classifier 2026-04-30T00:00:00Z 2026-07-15T00:00:00Z From a Colab notebook to v5.13: a RunPod-trained EfficientNet-V2-S over 897 car classes, shipping on-device as FP16 CoreML on iOS and TFLite on Android. https://reops.tech/blog/terraback-journey/ Building Terraback: A CLI for Reverse-Engineering Live Cloud Infrastructure into Terraform 2026-04-24T00:00:00Z 2026-04-24T00:00:00Z Building Terraback: a local-first CLI that reverse-engineers live AWS, Azure, and GCP infrastructure into clean, importable Terraform that plans zero-diff. https://reops.tech/blog/argus-llm/ ARGUS: My Approach to Putting an AI Agent in Front of a Metrics Backend 2026-04-24T00:00:00Z 2026-04-24T00:00:00Z Putting a local LLM agent in front of a Prometheus/Thanos metrics backend: baseline-aware alerting, a 4,800-to-2 query batching rewrite, and 7B-model lessons. https://reops.tech/blog/why-dns-failover-doesnt-work/ Why DNS Failover Doesn't Work (And What to Do Instead) 2025-02-15T00:00:00Z 2025-02-15T00:00:00Z Why DNS-based database failover fails in practice due to connection pools, resolver caching, and TCP behavior, and what solutions actually work. https://reops.tech/blog/infrastructure-cost-optimization-framework/ The Art of Right-Sizing: A Framework for Infrastructure Cost Decisions 2025-02-15T00:00:00Z 2025-02-15T00:00:00Z A practical framework for making infrastructure cost decisions that balance cost, risk, operational overhead, and business constraints. https://reops.tech/blog/evaluating-deployment-platform-complexity/ When Your Deployment Platform Becomes the Problem: Evaluating Overengineering 2025-02-15T00:00:00Z 2025-02-15T00:00:00Z A framework for evaluating deployment platforms and identifying when complexity has become overengineering. https://reops.tech/blog/reverse-engineering-cloud-terraform/ Reverse Engineering Existing Cloud Infrastructure into Terraform 2025-01-15T00:00:00Z 2025-01-15T00:00:00Z A practical guide to converting existing cloud infrastructure into Terraform code. Covers manual approaches, tooling options, and best practices. https://reops.tech/blog/kong-kubernetes-networking/ Troubleshooting Kong Gateway to Upstream Service Connectivity in Kubernetes 2025-01-15T00:00:00Z 2025-01-15T00:00:00Z A systematic guide to diagnosing and resolving Kong Gateway to upstream service connectivity issues in Kubernetes. https://reops.tech/blog/haproxy-ssl-multi-domain/ HAProxy SSL Termination Patterns for Multi-Domain Environments 2025-01-15T00:00:00Z 2025-01-15T00:00:00Z Practical patterns for implementing SSL termination with HAProxy when handling multiple domains using SNI routing.