Helpful notes

Quick reference for things you'll come back to.

The two phrases that run everything

Two short sentences run every tutor session. Worth saving them somewhere visible (Notepad, a sticky note, your phone).

To stop for the day, when you're done, type:

The tutor saves your progress, gives you your pick-up-next-time reminder, and tells you it's safe to close the window. (Capitalisation and punctuation are forgiving; "End lesson." or "end lesson" both work.)

To come back next time, open Git Bash and type:

Then once the tutor's running, type:

The tutor reads your progress and picks up where you left off.

Useful slash commands

"Slash commands" are special commands you type to the tutor that start with a slash. The tutor recognises these and acts on them instead of treating them as a normal message.

You don't need to memorise these; your tutor will introduce them as they come up. But if anything goes wrong, these are worth knowing.

/help: show the full list of commands the tutor knows.

/restore: undo the last thing the AI changed in your files. This is the safety net for "I let it do something and I'd like it back the way it was." If something's gone wrong, this is usually the first thing to try.

/clear: wipe the screen if it gets cluttered. Your conversation isn't lost; only what's visible.

/quit: leave the tutor cleanly. (Or /exit, same thing.)

/chat save <name>: save the current conversation under a name you can come back to. /chat resume <name> picks it up later. /chat list shows you all your saved conversations. Useful if you want to keep two threads going at once (e.g. for two different projects).

Things to remember — concepts and techniques from the curriculum, in order

Quick reference for the things your tutor walks you through. Useful for refreshing the bits you've half-forgotten.

The prompt → action → review loop (step 1)

The shape of every interaction with the AI. You give an instruction (the prompt) → the AI takes an action in the real world → you review what it did before deciding what's next. The review beat is the one beginners skip, and the one that matters most.

Writing prompts the AI can act on (step 3)

Four principles:

• Be specific. Write it like a brief, not a hint. Say what you want, what it should do, what it should avoid. The memorable test: "show your prompt to a friend with minimal context; if they'd be confused, the AI will be too."
• Give context. Who's it for, what's it for, what are the constraints. Don't assume the AI knows your situation.
• Show, don't just tell. An example of what you want is worth a paragraph of describing it.
• Split big jobs. Don't ask for the whole castle in one prompt; build it room by room. The phrase to remember: "let's divide this up along the logical seams."

Pointing at files with @ (step 4)

When you want the AI to look at a specific file, put @ in front of the filename. For example:

The AI reads the file before doing anything, so it knows what it's working with.

The review muscle — predict-then-check (step 5)

Before approving any change the AI proposes, say (or think) what you expect it to do. Then watch. When your prediction doesn't match what happens, that's the moment to investigate, not just click through.

Save-points (step 6)

Every time the tutor narrates "I'll save a checkpoint here", it's making a git commit, a snapshot of your files you can return to. /restore is the quick undo for the most recent AI change. For anything older, the tutor can take you back to any earlier save-point.

Commit vs push (step 7)

A commit is a save-point on your own computer. A push is sending those save-points up to GitHub (online). Commits protect your work from your edits going wrong. Pushes protect it from your laptop dying.

Plan before building (step 8)

When you want to build something (even small), the default move is "let's plan it first" before any code happens. Talk through what files would exist, what could go wrong, what order to do it in. Write the plan into a file (often called plan.md). The conversation is the lesson; the file is the artefact.

Troubleshooting prompts (step 9)

When something feels off, these phrasings work surprisingly often:

• "I'm seeing this: [paste the error]. What does it mean and how do I fix it?"
• "I expected X, but got Y. What might be causing that?"
• "This was working before you did X; what might have changed?"
• "What are 2 or 3 things that could be causing this? Don't change anything yet; let's think first." (The most important one: it stops the AI charging in to "fix" things wrong.)
• "@filename: have a look here and tell me if anything looks wrong."

Asking fresh AIs for things (step 10b closing)

Your tutor knows you. Other AIs (a fresh Gemini in another folder, or Claude, or any of them) don't. When you talk to a fresh one, describe what you want as an outcome, like a stranger. The launcher alias guide on the Starting your own projects page shows the shape.

Tokens and context windows — why long sessions sometimes get weird

Every AI conversation has a memory limit. The technical name for this is the context window, and what fills it up are called tokens (roughly: words and bits of words).

What you need to know:

• Long conversations cost more (the AI re-reads everything each turn) and get slower.
• Eventually the conversation gets so long the AI starts to forget the start. It doesn't tell you when this happens; things just get a bit off.
• If a session feels slow, or your tutor seems to have lost the plot, that's the sign. Either start a fresh conversation, or ask the current one to summarise where you are first so you can carry the summary into the new one.

Your tutor saves your progress in progress.md regardless, so even a long-conversation crash won't lose your learning. But day-to-day, shorter sessions tend to be sharper.

Things you can ask your tutor

If you ever feel stuck on a concept or want a different angle, these phrases almost always work. The tutor will adapt.

• "Can you explain that in simpler terms?"
• "What did you just do?"
• "Why isn't this working how I expected?"
• "Can you show me an example?"
• "Slow down, I want to follow this step by step."
• "I'm lost, can we go back to before the last change?"

And if the tutor itself is the thing failing, message Becky or the WhatsApp group. That's by design, not a fallback.