On this page
How to build AI agents from scratch for free
AI agents can use tools, run code, search the web, and plan steps. In this tutorial, we’ll build and test an agent with Google ADK.
Read the article →Writing / Engineering notes
Practical guides, experiments, and the details behind what I build. Follow the examples, inspect the code, and read the sources.
117 articles / Page 4 of 10
On this page
AI agents can use tools, run code, search the web, and plan steps. In this tutorial, we’ll build and test an agent with Google ADK.
Read the article →As a creator who relies on AI to help draft my blog posts, I kept running into a frustrating issue. When I'd copy text from ChatGPT, Claude, Gemini, etc, it looked perfect, but there was something hidden: invisible characters.
Google has released a new tool for developers called Google Antigravity IDE. This new software is built around Google’s advanced AI model, Gemini 3.
I’ve been using the Gemini CLI a lot lately for my coding projects. I really like how it helps me work faster right inside my terminal. But when I first started, I didn’t always get the best results.
The Gemini CLI is an open-source command-line tool that brings the power of Gemini (by Google) to your terminal. Keeping it up to date means you’ll get the latest features, fixes, and better performance.
Google AI Studio now includes a Build feature for generating apps from prompts. I’ll use it to create and preview an image-search app.
The Chrome DevTools Model Context Protocol (MCP) server lets a coding agent inspect pages and use browser debugging tools. I’ll show you how I connected it and tested it on a website.
Here are ten Git commands for inspecting changes, working with branches, and managing commits. I’ll explain what each does and when I use it.
This tutorial shows how to install OpenAI’s Codex extension in Visual Studio Code. We’ll use it to edit files, run commands, and review code changes.
Google’s “Nano Banana” image model brings new editing tools to the Gemini app. I’ll show how to change a photo and combine images while keeping a subject’s appearance consistent.
When I work with multiple AI coding agents, keeping their instruction files consistent takes extra work. AGENTS.md gives compatible agents a shared place to read project instructions.
I’ll show you how to select GPT-5 in Cursor and use it to improve a messy app. We’ll work through the setup and a few coding tasks.