Build a Stateful Agent with LangGraph and Trace It with Langfuse
A working LangGraph agent that keeps state across turns, calls real tools, and ships full traces to Langfuse. Real code, runnable end to end.
Writing
Thoughts on Cloud Computing, DevOps, and Software Engineering.
Sharing lessons learned from building scalable systems.
Build an MCP Client That Connects to Multiple Servers in Python
Most MCP tutorials stop at one client, one server. Real agents need many. This guide builds a Python client that connects to two MCP servers in parallel, prefixes their tools to avoid collisions, and hands them to Claude as Anthropic-format tool definitions.
Build a Tool-Using AI Agent with the Claude Agent SDK (Python)
Use Anthropic's official Claude Agent SDK to build a Python agent with custom tools, in-process MCP servers, PreToolUse hooks, and streaming output. Real code, no hand-waving.
PostgreSQL on Docker: Production Setup, Backup, and Performance Tuning
Run PostgreSQL in Docker with production-ready config. Covers initialization, persistent storage, automated backups with pg_dump, connection pooling, and performance tuning.
Kubernetes NGINX Ingress Controller: Setup, TLS, and Routing
Step-by-step guide to installing the NGINX Ingress Controller on Kubernetes, configuring path-based routing, and setting up automatic TLS certificates with cert-manager.
GitHub Actions CI/CD: Build and Push Docker Images with Layer Caching
A complete GitHub Actions workflow that builds a Docker image, caches layers between runs, and pushes to Docker Hub or GHCR. With copy-paste YAML and a comparison of cache strategies.
Docker Compose for Local Development: Node.js + PostgreSQL + Redis from Scratch
A hands-on guide to building a production-like local dev stack with Docker Compose. Covers service setup, volumes, health checks, environment variables, and hot reload with real working code.
Build Your First MCP Server in Python: A Hands-On Guide
Model Context Protocol is becoming the standard way to give LLMs access to tools and data. This guide walks you through building a real MCP server in Python, connecting it to Claude Code, and shipping it in under an hour.
Run a Local LLM Code Reviewer with Ollama and Continue.dev
A practical setup for a private, offline code reviewer. Pull a coding model in Ollama, wire it to VS Code through Continue, and review diffs without your code ever leaving the machine.
Ship a Remote MCP Server in TypeScript: From Local Dev to the Official Registry
Build a TypeScript MCP server with the official SDK, expose it over streamable HTTP, add OAuth 2.1, test it with the MCP Inspector, and publish it to the official MCP Registry. Production-grade setup, no hand-waving.
Build a Production RAG Pipeline with pgvector, Python, and the Anthropic API
A working RAG pipeline in 200 lines of Python: Postgres with pgvector, Voyage embeddings, Claude for generation, and an evaluation loop. Real commands, real costs, no hand-waving.
Self-Host LLMs with vLLM: A Production-Grade OpenAI-Compatible Server
Run open-source LLMs on your own GPU box and get an OpenAI-compatible API in one command. Covers install, PagedAttention, OpenAI server, performance tuning, and production deployment.
Ollama: Run Open-Source LLMs Locally with One Command
A hands-on guide to Ollama: install, pull a model, run it from the CLI, call it from Python and Node, build a custom Modelfile, and know when to use it instead of vLLM or a hosted API.
Build Production-Ready Docker Images: From 2GB to 100MB
Six practical techniques to shrink Docker images by 90%, cut deployment time, and reduce your attack surface. With copy-paste examples for Go, Node.js, and Python.
Building Scalable CI/CD Pipelines with Jenkins and GitLab
Best practices for building reliable deployment pipelines for engineering teams — from concept to production-grade pipeline.
Cloud-Native Architecture: From Monolith to Microservices
Migration journey from monolith to microservices using Kubernetes and AWS. Lessons learned during the transition process.
Load Testing with k6.io: Beginner's Guide
Practical tutorial on using k6.io for load testing. Includes example scripts and result interpretation for production environments.
Infrastructure Monitoring with Prometheus and Grafana
Complete guide to setting up monitoring for production infrastructure. From installation to creating meaningful dashboards.
Build a Multi-Agent Research Crew with CrewAI: Sequential and Hierarchical Processes
A hands-on guide to orchestrating multiple AI agents in CrewAI. Set up a researcher, analyst, and writer agent, run them through sequential and hierarchical processes, and get a structured research report out the other end.
Build an MCP Server with Python: A Practical Tutorial
Learn the Model Context Protocol by building a real MCP server with the Python SDK. Tools, resources, prompts, transport modes, and testing with the MCP Inspector, all with copy-paste code.
Structured Output Across LLM Providers: OpenAI, Anthropic, Gemini, Ollama
A side-by-side guide to forcing LLMs to return valid JSON. Real code for all four major providers, the gotchas that break production agents, and a fallback strategy for local models that do not support tool calling.
Build Your First MCP Server in TypeScript: A 30-Minute Hands-On Guide
Step-by-step tutorial to build a Model Context Protocol server in Node.js, expose tools, resources, and prompts, then connect it to Claude Desktop. Includes copy-paste code and the full TypeScript skeleton.
Run LLMs Locally with Ollama: From Install to a Production-Ready API
A hands-on walkthrough of running large language models on your own machine. Pull a model, hit the REST API, use the OpenAI-compatible endpoint, get structured output, and wire it all into a small RAG agent, all from one HTTP server.
Debug Any MCP Server in 5 Minutes with the MCP Inspector
A hands-on tour of the official MCP Inspector: launch it against npm, PyPI, or a local server, read the four tabs (Server, Resources, Prompts, Tools), and follow a workflow that catches the bugs you usually only find when a real agent connects.
Cut Your LLM Bill 90% with Claude Prompt Caching (A Practical Guide)
Prompt caching is the cheapest performance win in LLM apps. Here is how Anthropic, OpenAI, and Google price it, when to use 5-min vs 1-hour TTL, the lookback gotcha that silently breaks your cache, and a copy-paste Python pattern for tool-heavy agents.
Build Your First MCP Server in Python: A Practical Guide
MCP turns tools, files, and APIs into a standard protocol any LLM host can consume. Build a working server in 15 minutes with the Python SDK, then connect it to Claude Desktop or the MCP Inspector.
Build a Local AI Agent with Ollama and Function Calling
Run a tool-using LLM agent entirely on your machine. No API keys, no rate limits, no data leaving your laptop. Step-by-step with Ollama, a real tool, and a Python loop you can extend.
Build a Local MCP Server in Python and Wire It to Claude Code
A hands-on walkthrough of the Model Context Protocol: build a stdio MCP server in ~30 lines with FastMCP, expose filesystem and git tools, debug it with the MCP Inspector, and connect it to Claude Code or Cursor.
OpenAI Agents SDK: Handoffs, Guardrails, and Tracing in One 20-Minute Build
Build a real triage agent with the OpenAI Agents SDK: tools, handoffs to specialists, input guardrails that trip on out-of-scope requests, and automatic traces to platform.openai.com. Real code, copy-paste.