Challenge 3: Why "Most AI Features" Doesn't Mean "Easiest" -- Solution
Walkthrough

This assumption is backwards because Descript's own AI features
(Overdub, Studio Sound, Underlord, Generative B-Roll) are tools you
have to deliberately choose to invoke and know how to use well --
they don't run automatically the way Chapters 6 and 7's pipelines do,
and they don't replace the underlying transcript-based editing
paradigm the presenter still has to learn. Having more AI capability
available is not the same as having more automation happening on your
behalf by default; per this chapter, Descript automates nothing you
don't explicitly ask it to, which is the opposite of "easy" in the
sense the other tools in this course provide it.

Concretely: Descript has no automatic cursor-aware zoom at all, so
achieving Chapter 2's own legibility criterion requires manual timeline
work, unlike every capture-time recorder in Chapters 3-5 where
legibility improves automatically as a side effect of just recording.
Reaching Overdub's own highest narration ceiling requires writing a
real script, which is real, deliberate effort, not a shortcut.
Reviewing filler-word removal and Studio Sound's stem separation both
require active editorial judgment rather than trusting a default
output. The richness of Descript's own feature set is exactly why it
carries this course's steepest learning curve -- more available
capability creates more decisions the presenter has to actually make,
not fewer.

WHY THIS WORKS AS AN ANSWER
------------------------------
This exercise checks that the reader distinguishes "has more powerful
features" from "requires less effort to get a good result" --
correctly identifying that Descript's category (full manual editing
suite) is defined by the opposite of automatic ease, even though it
happens to include an unusually rich set of AI-assisted tools.