The Blog

Model Context Protocol (MCP) is a great protocol but if your company is built around it as the core product, you're not gonna make it. Here's why.

Running agentic AI workflows with the Qodo Command CLI is a powerful way to automate tasks but what's even cooler is that you can also automate the whole fine-tuning of the agentic workflow process itself USING THE AGENT!

Getting a security report for security vulnerabilities and misconfiguration issues of your GitHub project is a good start but can we leverage AI to also remediate all of these issues automatically through agentic workflow? Yes and I will show you how I do that with Qodo CLI Agentic Workflow

Learn how to set up a TV sleep timer using Home Assistant automation, Helpers, and Automations to manage your TV's power state easily.

Fun and useful automation for Shabbat observant families to announce the candle lighting time using Home Assistant.

Demystifying the 3 dimensions of cookie-based authentication: CORS, SameSite, and CSRF.

Gamified learning is a great way to engage developers and teach them new skills. I share my experience building a game to teach developers about open-source security, playing Lakera's LLM prompt injection game and cheering for Israeli gamified learning startup Wilco.

You're probably facing some DevRel failures or marketing failures. Maybe your product and marketing strategies are actually outdated and causing customer churn, and overall frustration?

Learn how to build powerful command-line apps without a single third-party dependency using Node.js core modules.

Practical and hands-on guide to getting started with Neural Networks in JavaScript using the Brain.js library to build a simple neural network to predict if a number is even or odd and more.

Developer Advocates and Engineers can leverage Generative AI to speed up their work and make them more productive. Here's a practical example from my day-to-day.

Building with Large Language Models (LLMs) requires context and metadata. The `llms.txt` file format is a simple text file that provides LLMs with relevant context and metadata.

What are some common anti patterns and signs of tight coupling in a Node.js codebase and the challenges they present? Let's unfold some messy code and learn how the CJS module system and the use of globals has to do with it.

If you're building LLM and AI-powered chatbots like me you might need to read and parse PDFs or create PDFs in Node.js. Here's how to do it with PDF.js and PDF Lib.

How do you handle TypeScript, dual ESM and CJS publishing, and the JavaScript toolchain in 2025? Here's a brief overview of the current state of the ecosystem and the tooling I personally use.

How to set up Home Assistant YouTube DNS blocking with AdGuard and Lovelace buttons for a more action friendly interface.

Learn how I got the Starlight documentation framework in Astro to create a gated content website with authentication for my Bun Security course

Step-by-step tutorial on configuring a Google Cloud project and storing images in Google Cloud Storage.

Imagine if we applied behavioral economics principles to application security methodologies and practices, what would be able to unlock? System1 and System2, All Systems Go.

Can Astro automatically import components in markdown files? Yes, it can! Here's how to do it thanks to Chris Swithinbank and his Astro Auto Import package.

This article explores the use of `Promise.withResolvers` in Node.js tests, providing examples and refactoring techniques to handle nested tests and signal their completion effectively. It also discusses the limitations of the `Promise.withResolvers` API in different Node.js versions.

Learn how to supercharge your Vue.js 3 app with TanStack Query. Discover efficient data fetching, caching, and state management in this practical refactoring guide.

The rise of zero dependency JavaScript with packages like `neotraverse` and the controversy around the `axobject-query` package demonstrate the different perspectives and trade-offs that developers and maintainers need to consider when building and maintaining JavaScript applications.

How about we try a different approach to ChatGPT, Google Gemini or Anthropic's Claude? Learn how to run a local LLM model for inference so you can access it offline and without incurring costs beyond your own hardware compute.

Current adoption craze for GenAI tools like ChatGPT bring hidden costs in the form of privacy, security, data leakage, latency and availability. The future isn't gloom though, as the future of LLMs is in local-first offline inference, open LLMs, consumer-grade GPU acceleration and micro fine-tuning model training. How and why? Read on.