Introduction: Amazon Elastic Container Registry (ECR) is a fully managed container registry service provided by AWS. It enables developers to store, manage, and deploy Docker container images securely. In this guide, we’ll explore how to provision a new AWS ECR using Terraform, a popular Infrastructure as Code (IaC) tool. We’ll cover not only the steps […]
Read more →Year: 2024
Prompt Templates and Versioning: Building Maintainable LLM Applications
Introduction: Production LLM applications need structured prompt management—not ad-hoc string concatenation scattered across code. Prompt templates provide reusable, parameterized prompts with consistent formatting. Versioning enables A/B testing, rollbacks, and tracking which prompts produced which results. This guide covers practical prompt template patterns: template engines and variable substitution, prompt registries, version control strategies, A/B testing frameworks, […]
Read more →Deploying LLM Applications on Cloud Run: A Complete Guide
Last year, I deployed our first LLM application to Cloud Run. What should have taken hours took three days. Cold starts killed our latency. Memory limits caused crashes. Timeouts broke long-running requests. After deploying 20+ LLM applications to Cloud Run, I’ve learned what works and what doesn’t. Here’s the complete guide. Figure 1: Cloud Run […]
Read more →Prompt Optimization Strategies: From Structure to Automatic Refinement
Introduction: Prompt optimization is the systematic process of improving prompts to achieve better LLM outputs—higher accuracy, more consistent formatting, reduced latency, and lower costs. Unlike ad-hoc prompt engineering, optimization treats prompts as artifacts that can be measured, tested, and iteratively improved. This guide covers the techniques that make prompts more effective: structural patterns that improve […]
Read more →Platform Engineering: Building Internal Developer Platforms That Actually Work
After spending two decades building and scaling engineering organizations, I’ve come to a conclusion that might seem counterintuitive: the biggest productivity killer in most enterprises isn’t technical debt, legacy systems, or even organizational politics. It’s cognitive load. Developers spend an unconscionable amount of time navigating infrastructure complexity instead of solving business problems. Platform engineering, done […]
Read more →Building Production RAG Applications with LangChain: From Document Ingestion to Conversational AI
Introduction: LangChain has emerged as the dominant framework for building production Retrieval-Augmented Generation (RAG) applications, providing abstractions for document loading, text splitting, embedding, vector storage, and retrieval chains. By late 2023, LangChain reached production maturity with improved stability, better documentation, and enterprise-ready features. After deploying LangChain-based RAG systems across multiple organizations, I’ve found that its […]
Read more →