Practical articles on Java, microservices, system design, AI engineering, and the future of software development. No fluff — only production-tested insights.
As AI systems become increasingly complex, ensuring their reliability and performance is crucial. This blog post delves into the observability of large language models (LLMs), focusing on tracing, logging, and monitoring to maintain robust AI systems.
Discover the intricacies of deploying Large Language Model (LLM) applications at scale. Learn from real-world experiences, explore architecture patterns, and understand the challenges and best practices for successful implementation in production environments.
Explore the role of feature stores in modern machine learning pipelines, focusing on Feast and Tecton. Learn how these tools streamline feature management, enhance scalability, and integrate with cloud-native architectures.
As AI models become integral to modern applications, optimizing their cost is crucial. This post explores strategies like caching, batching, and model selection to reduce expenses while maintaining performance. Learn how to implement these techniques effectively in your systems.
Explore the emerging trend of structured output from large language models (LLMs) using JSON mode and tool calling. Learn how these advancements are reshaping software development, offering new possibilities for automation, integration, and system design.
Discover how AI code generation tools like GitHub Copilot are transforming software development workflows. Learn how to integrate these tools effectively, understand their benefits and limitations, and explore real-world use cases and best practices for modern engineering teams.
Explore the evolution of agentic workflows from basic task chains to sophisticated AI agents. Discover why this shift matters in 2025, how it impacts system design, and best practices for implementation.
Explore the intricacies of vector search, a pivotal technology in modern AI systems. Learn how embeddings transform data retrieval, discover real-world applications, and understand the challenges and best practices for deploying vector search in production.
Explore the cutting-edge of AI engineering with function calling in large language models (LLMs). Learn how to build tool-using AI agents, understand their architecture, and discover best practices for integrating them into modern software systems.
As AI models become integral to production systems, evaluating their quality is crucial. This post explores how to measure LLM quality in production, offering insights into real-world applications, challenges, and best practices for engineers.
Explore the intricacies of building recommendation systems using collaborative filtering. This post delves into the technical aspects, real-world applications, and challenges, offering insights for engineers looking to implement these systems in production.
In 2026, the landscape of AI-driven applications has evolved significantly. This post explores the nuances of LangChain and LlamaIndex, two powerful tools for building Retrieval-Augmented Generation (RAG) applications, and provides insights into their real-world applications, trade-offs, and best practices.