Category
Articles
9 posts
Technical articles on software engineering, architecture, AI and operations. Written by practitioners, with real data.
LLMs in Production: Costs, Latency, and the Metrics Nobody Talks About
The reality of operating LLMs in production: token costs at scale, latency budgets, caching, model routing, and the hidden costs of prompt engineering.
Infrastructure as Code: Terraform vs Pulumi vs CDK
Practical comparison of Terraform, Pulumi, and AWS CDK based on real projects. Learning curves, multi-cloud support, testing, and when to choose each one.
Voice AI in Hospitality: Architecture of a Hotel Callbot
Detailed architecture of a hotel callbot in production. STT, intent detection, PMS integration, multilingual handling and operational metrics.
RAG vs Fine-Tuning: Choosing the Right Approach for Your Business
RAG and fine-tuning solve different problems. Cost, latency, accuracy and maintenance compared with real benchmarks from production projects.
AI in customer service: beyond the chatbot
Chatbots were just the beginning. Next-generation conversational AI understands context, solves problems, and scales like an entire team. Here's how it works.
Kubernetes in Production: Lessons from 3 Years Operating Clusters
Hard-won lessons from running Kubernetes in production for 3 years. When it is worth it, cluster sizing, networking gotchas, security hardening and cost optimization.
Microservices Observability: Metrics, Traces and Logs That Actually Matter
Beyond basics: which metrics to instrument, correlating traces with business outcomes, avoiding alert fatigue.
How We Built a Real-Time Data Pipeline with Kafka and Flink
Production war story of building a real-time logistics tracking pipeline. Schema evolution, exactly-once semantics, backpressure, throughput metrics.
CI/CD Without DevOps: Ship in 10 Minutes, Save EUR 4K/Month
A CI/CD pipeline that a dev team can own. GitHub Actions free tier, under-10-minute build target, and EUR 4,000-6,000/month saved vs. a dedicated DevOps hire.