Meet Manus — what it is and who makes it

The concept

Manus is a general autonomous agent that plans, browses, builds and delivers a result made by Manus. The models behind it are a set of frontier models orchestrated by a planning loop with a browser and a code sandbox. None of that matters on its own — what matters is that you know what kind of worker you have hired. At a task with a finish line that can be reached by doing many small steps — research, comparison, a document, a small site is the job you hand it. At knowing when to stop, and at any task where you cannot say in one sentence what a good result looks like is the job you keep.

Most people come to a course like this expecting a list of magic words. There is no such list. What there is, is a tool that produces a delivered artefact — a report, a spreadsheet, a small site, a set of files — rather than an answer, and produces it at a speed no human matches — which means the skill is not in writing the prompt, it is in knowing what a good answer looks like so you can tell the difference.

Here is the first thing to try, worded the way you will word things for the rest of the course:

Read the answer twice. The first read is for the content; the second is for the shape — did it answer the question you asked, or the question it found easiest? That second read is the habit this whole course is built on.

I need to choose a laptop under a fixed budget. Write the plan first and show it to me before doing any research, then compare five options with a source and a date on every price, and mark anything you cannot find as NOT FOUND.