Courses

In this tutorial, you’ll build a practical AI agent that can receive a user prompt, decide whether it needs to use a tool, execute that tool in PHP, store conversation history in MySQL, and continue reasoning until it produces a final answ…

You've seen it a hundred times: the Wi-Fi drops, Chrome shrugs, and a little pixelated T-Rex appears, ready to sprint through a desert the moment you hit the spacebar. That tiny game, hidden behind the "No Internet" error since 2014, is pl…

Every B2B SaaS product with a compliance requirement (like banking, lending, payroll, or crypto) hits the same wall early on: before you can let a business use your platform, you need to verify who they are. That means collecting a busines…

When learning C, it's easy to get stuck building text-based terminal applications that simply ask for user input and print a result back out. While those are great for learning the basics of the language, deeply understanding CPU architect…

Whether you're designing robotics, analyzing fluid dynamics (CFD), or working through complex engineering data, learning to code is one of the most effective ways to boost your workflow and technical analysis. We’ve just released a compreh…

Sometimes you don't want to change the actual content of a PDF. You simply want to add a colored layer over part or all of the document. This can be useful for creating branded reports, adding colored backgrounds, highlighting printed copi…

Today, diffusion models have become one of the most influential families of generative AI systems. They power applications ranging from image synthesis and editing to video generation, scientific discovery, and multimodal content creation.…

PDF editing isn't limited to adding signatures or merging documents. Sometimes you simply want to improve the appearance of a PDF by increasing brightness, boosting contrast, adding blur, converting it to grayscale, or applying creative vi…

When your AI agent serves more than one person, every tool call must answer: who's the agent acting for? Let's learn how to solve this by building an AI agent that connects with Slack and GitHub. A Slack read uses that user's workspace. A …

Picture this: it's 4pm on a Friday, and your team has just merged the last feature for the sprint. But your product manager asks for a new build on TestFlight by the end of the day so the client can review it over the weekend. You open Xco…

Causal inference for LLM-based AI features is no longer theoretical. Airbnb, Netflix, Lyft, and Uber have published detailed engineering blog posts describing exactly how they measure the causal impact of product changes on user behavior. …

Your AI product shipped an agent-mode opt-in six months ago. You ran a propensity analysis, adjusted for engagement tier and query confidence, and reported a clean +8 percentage-point lift in task completion. The number made it into the qu…

The gap between a demo that impresses and a system you can trust is measured in evals. I want to start with a story that's happening in hundreds of engineering teams right now. A team builds a RAG application for legal research. They test …

In 2022, I built a small micro-SaaS in my spare time and eventually sold it for a few thousand dollars. And today, with AI tools, it probably would've been even easier to build. But what has changed dramatically isn't the cost of building …

Static sites are having a moment, and it makes sense. A folder of HTML, CSS, and JavaScript files is fast to load, cheap to host, and very hard to break. Tools like Astro, Eleventy, and Hugo build that folder for you from Markdown files an…