JavaLearn Something Along the Way
Pick one CS concept your app depends on and really learn it.
Check your table assignment for today’s section.
Building an app with Claude is fast—sometimes too fast. It’s easy to end up with a working app that uses powerful ideas you’ve never stopped to understand. Today you’ll slow down and pick one.
You’re not going to touch your code today. No tracing, no editing, no “explain this file.” Instead, you’ll use Claude as a tutor—the way you might talk to a really patient TA—and use what your app does as the example. The goal is to leave today understanding one idea well enough to explain it to a friend.
Find a Concept Worth LearningFind a Concept Worth Learning
Start by picking something. If you already have a concept in mind—a data structure, an algorithm, a pattern your app relies on—great. If not, ask Claude to help you pick. The best concepts are ones your app really depends on, and ones you couldn’t confidently explain right now.
Try it: Ask Claude to surface a concept worth your time.
Based on what my app does, which CS idea is the most important one I should really understand before this class ends?
If I had to explain one idea from my app in an interview—not the code, just the idea—what should it be?
Pick one concept and stick with it for the rest of the activity. Don’t try to cover five things shallowly. One idea, understood deeply, is the goal.
Learn the Idea, Not the ImplementationLearn the Idea, Not the Implementation
Now ask Claude to teach it to you from scratch. Not with code. Not by opening your files. Just the idea, the way you’d explain it to someone who’s never programmed.
Push for analogies, simple examples, and the why. Every concept in CS was invented to solve a problem. If you understand what problem it solves, the rest falls into place.
Try it: Ask Claude to teach the concept conceptually.
Explain <concept> to me from scratch, like I’m encountering it for the first time. Use an analogy, not code.
Give me the simplest example of <concept> that has nothing to do with my app, so I can see the idea on its own.
What would go wrong from a user’s perspective in my app if <concept> didn’t exist or worked badly?
If an explanation feels hand-wavy, push back. Ask Claude to slow down, to try a different analogy, to use smaller words. A good tutor doesn’t mind going slower—and neither does Claude.
Teach It BackTeach It Back
You don’t really understand something until you can explain it. Now flip the conversation: you teach the concept, and Claude checks your work.
This is the most valuable part of the activity, and the part most students will want to skip. Don’t. Saying the idea out loud (or typing it out) is how you find the gaps in your own understanding.
Try it: Explain the concept in your own words.
I’m going to explain <concept> to you in my own words. Tell me what I get wrong, what I leave out, and where my explanation is unclear.
Give me a realistic scenario—not from my app—where I’d need <concept>, and ask me how I’d think about it.
When Claude points out something you got wrong, don’t just accept the correction. Ask Claude to explain why you were wrong, and try again.
Connect It OutwardConnect It Outward
The best way to lock in a new concept is to connect it to things you already know. Where else does this idea show up? How would your app feel different if the concept worked differently? What’s the next thing to learn?
Try it: Place the concept in a bigger picture.
Where else in the real world does <concept> show up? Give me three examples that have nothing to do with my app.
How would the user experience of my app change if <concept> worked differently or was missing entirely?
One-Sentence TakeawayOne-Sentence Takeaway
Before you leave, write one sentence in your head (or out loud to a neighbor) that starts with:
“Today I learned that <concept> is…”
If you can finish that sentence confidently, the activity worked. If you can’t, that’s useful information—go back and ask Claude one more “why” question before class ends.
Before You Leave: Commit and PushBefore You Leave: Commit and Push
Before getting your attendance scanned, make sure you commit and push your work. You can ask Claude to do this for you (try “please commit and push my work”), or use the Git integration in Android Studio.
Your Claude Code session transcripts are saved automatically with each commit. We use these logs to track your progress, so a push is required before you leave.
AttendanceAttendance
Once you’ve committed and pushed, show your progress to a staff member. They’ll scan your QR code for attendance.