·15 min readAI
What agentic coding actually looks like
Agentic coding changed how I build software. Not in the way the hype suggests.
AI
16 posts
·16 min readAI
Hermes Agent by Nous Research: the AI agent that actually cares about security
What Hermes Agent is, how it compares to OpenClaw on security and usability, and why it earned my trust.
·10 min readAI
How I would design an ad platform for LLMs
A technical breakdown of how a middleware ad layer for LLM APIs could work, why the economics demand it, and whether it should exist at all.
·11 min readAI
Building RAG pipelines with local models
How to build a retrieval-augmented generation pipeline using local models and your own documents, without sending data to cloud APIs.
·3 min readAI
Using OpenRouter to access multiple AI models
How OpenRouter gives you a single API to access models from OpenAI, Anthropic, Google, and others without managing multiple accounts.
·3 min readAI
How agent skills work
What agent skills are, how they extend AI coding assistants with reusable workflows, and why they matter for developer productivity.
·3 min readAI
AI-assisted code review workflows
How I use AI tools to review code before committing, catch bugs early, and maintain consistency across projects.
·12 min readAI
What is an MCP server and why should you care?
An introduction to the Model Context Protocol, what MCP servers are, and how they let AI assistants interact with external tools and data.
·11 min readAI
Getting structured output from language models
Techniques for getting LLMs to return JSON, typed objects, and other structured formats reliably, from prompt engineering to constrained decoding.
·2 min readAI
OpenCode: an open-source AI coding assistant
A look at OpenCode, an open-source terminal-based AI coding tool, and how it fits into my development workflow.
·9 min readAI
Fine-tuning small language models for specific tasks
A practical introduction to fine-tuning small LLMs for domain-specific tasks using tools like Unsloth and LoRA.
·4 min readAI
Comparing AI coding assistants: Claude Code, Cline, and OpenCode
An honest comparison of the AI coding tools I have used, what each does well, and which one fits different workflows.
·2 min readAI
Getting started with Open WebUI and Ollama
How to run local LLMs on your own machine with Ollama and put a clean web interface on top with Open WebUI.
·16 min readAI
Building an MCP server with TypeScript
A step-by-step guide to building your own Model Context Protocol server in TypeScript to give AI assistants access to custom tools.
·16 min readAI
What HuggingFace actually is
I thought HuggingFace was just GitHub for AI models, but that comparison sells it way short.
·12 min readAI
Running local LLMs on a consumer GPU
What you need to run large language models locally, which models fit on consumer hardware, and how to get the best performance.