24 posts tagged with "AI"

A good Scrimba Explain prompt names the topic, the audience, and the slides you want. I ran the same RAG prompt through three teaching styles, attached a Markdown file, and built a three-lesson playlist, seven explainers in total. Professor was not noticeably deeper than Standard, which suggests the prompt text, not the picker, sets the depth.

If you do not know what Explain is yet, the reference page covers entry points and quotas, and the full review covers whether the output is any good. This post is only about the web composer at scrimba.com/explain↗ (opens in a new tab): what to type, which style to pick, and which clicks cost you an explainer.

Scrimba Explain exposes two MCP endpoints. Claude Code connects to either with one command or one JSON file, reads your repository, and streams a narrated video lesson into Scrimba. Drafts cost nothing until someone opens and claims the link. I ran both endpoints against a public Anthropic repo and a merged pull request, and this post is what came back, including the parts that went wrong.

Every Scrimba lesson you can open has an EXPLAIN button in its header. Press it while paused, type a question, and Scrimba builds a short narrated video from that exact lesson: its files, the code you highlighted and what the teacher has said so far. It costs one explainer from your allowance (10 for life on a free account, 100 a month on Pro), and the result stays attached to the lesson.

I pressed it once, on the "Chunking text from documents" lesson in Learn RAG, with a deliberately picky prompt. This post is what got sent, what came back, and the three moments in a course where I think it earns its cost.

Scrimba Explain turns a typed question into a narrated video with code, diff and diagram slides, ending in a quiz when you ask for one, and it runs from a prompt, a Chrome tab or a coding agent. NotebookLM Video Overviews turn the documents you have already collected in a notebook into a narrated slideshow. For understanding a concept or a piece of code, Explain is the better fit. For a video summary of your own PDFs, lecture notes or a folder of docs, NotebookLM is the one to reach for.

One caveat before the table. The Scrimba side of this comparison is first-hand: I generated the explainers, read the transcripts and took the quizzes. The NotebookLM side is not. Google's NotebookLM sat behind a corporate sign-in on the machine I had, so every NotebookLM claim below comes from Google's own help pages and blog posts, each linked where it appears. Anything Google does not document is marked as unverified rather than guessed.

Scrimba Explain turns a question into a short narrated video explainer, complete with diagrams, code walkthroughs and, most of the time, a quiz at the end. A free Scrimba account gets 10 explainers for life, Pro gets 100 a month, and it works in the browser, inside Scrimba lessons, in ChatGPT, and inside coding agents like Claude Code through MCP. Most AI coding tools compete to write your code faster. This one explains it.

The best interactive coding platforms in 2026 are Scrimba, freeCodeCamp, Codecademy, Boot.dev, Exercism, and Codewars, because each one makes you write and run real code rather than watch someone else do it. That distinction matters more this year than it used to. When an AI will produce a working answer on demand, the platforms worth your time are the ones that keep your own hands on the keyboard, and my honest take is that the right pick depends less on the brand than on how hard it stops you from copy-pasting your way through.

The fastest way to get better at reading code is to read more of it on purpose: in small pieces, out loud, and forcing yourself to predict what each line does before you run it. In 2026 that has quietly become the highest-leverage skill a self-taught developer can build, because AI writes the first draft now and your real job is to verify it. My honest take, as an engineer who learned the hard way through 42 Network rather than by prompting: most beginners are drilling the half of the job the machine already does, and skipping the half interviewers now test for.

You build coding experience without a job by manufacturing the proof a job would have given you: shipped projects real people use, open source contributions with your name on the merge, small freelance or volunteer work, and public build logs that show how you think. In 2026 that is not a clever workaround. It is the main road, because the entry-level rung that used to hand beginners their first experience has largely collapsed. I learned to code through the 42 Network rather than a CS degree or a bootcamp, so I built every hour of my early experience without an employer, and the tactics below are the ones that actually move a resume from ignored to interview.

If you learn well from reading and you can hold yourself to a practice schedule, ChatGPT will teach you a surprising amount of coding for free. For most beginners, a paid platform like Scrimba earns its subscription by forcing you to write and run the code yourself, which is the exact step a chatbot lets you skip. Below is the honest version of that trade, weighed against 2026 research rather than affiliate enthusiasm. I learned to code the slow way at 42 Network, not on Scrimba, so read this as a comparison from someone with no course to graduate from.

Context engineering is the practice of deciding what information an AI model sees before it writes a single line of code: the files, docs, examples, rules, and tools you load into its context window. It is the skill that quietly absorbed prompt engineering over the past year. My honest take, after using these tools daily as an engineer who learned to code the self-taught route through 42 Network: the name is new and a little buzzy, but the job underneath it is real, and it happens to be good news for self-taught developers, because it rewards understanding a codebase over memorizing clever phrasing.