Bonus · Reference Card
Bonuses & References
The Subject Playbooks

Subject Cheat Sheet: STEM, Humanities, Languages, CS

Reference card Four playbooks · two prompts each Pairs with Lesson 3.3

Same engine, different gears.

Active recall (Lesson 3.3) works in every subject. The specifics bend a little depending on what you're studying. This page expands the four subject playbooks from 3.3:STEM, Humanities, Languages, CS:with a coaching prompt, a recall prompt, and the subject-specific honesty trap for each. Save this page once; come back to it whenever you start a new class.

How to use this page

Pick the playbook that matches the class. Copy the prompts. Fill in the brackets with your actual class name, topic, and material. The traps section at the bottom of each playbook tells you the move that crosses the Honest Work Code line for that specific subject: different for STEM than for Humanities than for CS. Read your class's trap before you skip it.

🧪 STEM: math, physics, chem, bio

STEM is about working problems, not memorizing answers. Two prompts: the coaching prompt (you solve, Claude guides) and the practice generator (Claude writes you problems to drill on).

STEM · "coach me, don't solve it"
I'm working on a [subject] problem. I want to solve it myself. Your job is to be my coach, NOT to give me the answer. Problem: [paste] Here's how I want this to work: 1. Don't show me the full solution. 2. Ask me what my first step would be. 3. If my first step is right: confirm and ask me what's next. 4. If my first step is wrong: DON'T tell me the right step. Ask a guiding question that helps me see what I missed (e.g., "what does the problem tell you about [variable]?" or "what equation describes this kind of system?"). 5. Continue until I get to the answer. 6. After I have it, show me the cleanest version of the full solution and tell me where I struggled: so I know what to drill. Subject: [class + level] Topic: [specific concept] Be patient but specific. If I'm stuck for 2–3 questions in a row, give me a bigger hint: but never the answer.
STEM · practice problem generator
I'm studying [topic] for [class: e.g., "Calc 1, integration techniques"] and I need to drill on it. Generate me a practice set: - 5 problems at "I get the basics" level - 3 problems at "exam-shaped, mixed concepts" level - 2 problems at "this would be the hardest one on the test" level For each problem, do NOT include the solution. Number them 1–10. After I work them on paper, I'll come back and tell you which numbers I want walked through. THEN you can show the solution path: but coach me on it the same way you do in the "coach me, don't solve it" prompt: ask me what my first step would have been before showing yours. Topic specifics: [optional: sub-topic, formula sheet I'm allowed, calculator allowed or not, etc.]
⚠️

STEM honesty trap: the photo paste

The trap: snap a photo of the problem set, paste it, ask Claude to "solve it." You get a number you can't reproduce on the exam. The fix is the coaching prompt above: same time investment, real learning.

📚 Humanities: history, lit, philosophy, polisci

Humanities is about argument and evidence, not memorizing facts. Two prompts: the Socratic sparring partner (your take gets stress-tested) and the reading-comprehension test (Claude quizzes you on what you actually understood).

Humanities · Socratic sparring partner
I'm preparing for [class] and I want to test my thinking on [topic / question / argument]. Be a Socratic sparring partner. Specifically: 1. I'll state my current take on the topic in 2–3 sentences. 2. Ask me ONE pointed question that probes the weakest part of my reasoning. 3. After I respond, identify whether my answer addressed the weakness or sidestepped it. 4. If sidestepped: ask the question again, sharper. 5. After 4–5 rounds, give me a debrief: - Where my argument is strongest - Where it's weakest - One counter-argument a smart opponent would raise that I should be ready to answer - One source or thinker I should engage with that would complicate or strengthen my view Be intellectually rigorous, not nice. The point is to make my actual thinking sharper, not to validate it. My take: [your argument] Class context: [name + level]
Humanities · reading-comprehension test
I just read [text: author, title, chapters or page range]. Test whether I actually understood it. Ask me, one at a time: 1. ONE question about the central argument or thesis. Don't tell me if I'm right: wait until I answer, then probe. 2. ONE question about evidence the author used (which examples, which sources, which claims). 3. ONE question about a counter-argument the author addressed (or should have). 4. ONE question about how this text connects to [other text we've read in this class: name it] or to a broader debate in [discipline]. 5. ONE question about something the author left out, glossed over, or assumed without arguing. After my answers, give me a one-paragraph debrief: what I clearly understood, what I missed, and one specific passage to re-read. Don't summarize the text up front. The whole point is to find out what I retained, not to give me the cheat sheet.
⚠️

Humanities honesty trap: the thesis handoff

The biggest line in humanities: asking Claude to write your thesis or your argument. A reading-comp test is fine. A sparring partner is fine. "What's a good thesis for an essay on X?" is not: that's the part that's supposed to be yours. If you find yourself there, switch to the M4.3 brainstorm prompt (you generate, Claude reflects).

🌍 Languages: Spanish, French, Mandarin, anything new

The rare subject where you can ethically use AI as a conversation partner as much as you want: because the whole goal is communicative skill, and conversation is what builds it. Voice mode is a killer feature here. Two prompts: the conversation partner (immersion) and the grammar-drill prompt (targeted practice on what's tripping you up).

Languages · conversation partner (voice mode loves this)
I'm learning [language] at [level: beginner / intermediate / advanced / specific course like "Spanish 201"]. Be my conversation partner. Specifically: 1. We're going to have a conversation entirely in [language] about [topic: e.g., "ordering food at a restaurant" or "describing my weekend" or "discussing climate policy"]. 2. Match my level: slightly above is fine (a stretch helps), but don't drown me in vocabulary I don't know. 3. After every 3–4 of my messages, pause and tell me (in English): - One thing I said well - One mistake I made (grammar, word choice, or naturalness):show the corrected version - One word or phrase I should have used that would have sounded more native 4. Then continue the conversation in [language]. Use voice mode if I tell you I'm walking around: I want to practice speaking, not just typing. Otherwise, text is fine. Don't switch to English unless I ask. The whole point is the immersion.
Languages · grammar drill on a specific weakness
I'm learning [language] and I keep getting [specific grammar concept: e.g., "Spanish subjunctive mood after expressions of doubt" or "French passé composé vs imparfait" or "Mandarin tone changes when a third tone is followed by another third tone"] wrong. Drill me on it. Specifically: 1. Give me 10 sentences in English where I have to translate to [language] using this grammar concept. 2. Mix the difficulty: some obvious, some that look like the rule but actually need an exception. 3. Don't give me the answers up front. 4. After I attempt all 10, grade them: ✓ correct / ✗ wrong / ~ partially right (and explain the partial). 5. For every wrong one, give me the correct version AND name what specifically I got wrong (vocab? conjugation? word order? tone?). 6. After the grade, generate 5 more sentences targeting just the patterns I missed. Stay in drill mode. No filler conversation. I'm here to fix one thing.
⚠️

Languages honesty trap: the homework auto-translator

Conversation practice is a green-zone use; chunking your written homework into Claude and asking for translations is not. The point of homework is to force the recall; auto-translating skips the recall and gets you a grade you didn't earn. The grammar-drill prompt above is the right alternative: same kind of practice, none of the homework crossover. If a class explicitly bans AI-assisted translation tools, that ban includes Claude.

💻 Intro coding: CS1, web dev, data science

Coding is where AI is most powerful AND where students most easily lose the skill. CS departments have gotten very good at spotting AI-written submissions. Two prompts: "explain my error, don't fix it" (debugging) and the code review (Claude critiques what you wrote, doesn't write it).

Coding · "explain my error, don't fix it"
I'm taking [class: e.g., "CS101 in Python"] and I'm stuck on a problem. Here's my code and the error. Code: [paste your code] Error: [paste the error message] What I'm trying to do: [describe in one sentence] Don't give me the fixed code. Instead: 1. Explain what the error message actually means in plain language. 2. Tell me what part of MY code is causing it (point to the specific line). 3. Ask me a question that would help me figure out the fix on my own. 4. Wait for my next attempt. If I'm wrong twice in a row on the same fix, give me a slightly bigger hint: but still not the working code.
Coding · code review (you wrote it, Claude critiques)
I just wrote this code for [class + assignment description]. I want a code review BEFORE I submit. Don't rewrite it for me. Code: [paste] What it's supposed to do: [1–2 sentences] Review it for: 1. Correctness: does it actually do what I described? Walk through one example input mentally and tell me what happens. 2. Style: anything that's hard to read, badly named, or against the conventions of [language]? Point to specific lines. 3. Edge cases: what input would break this? List 2–3 specific cases I should test. 4. Concept gaps: does my code suggest I'm misunderstanding any part of [topic: e.g., "recursion" or "list comprehensions" or "async/await"]? Do NOT give me rewritten code. Tell me where to look and what to think about. I'll fix it myself.
⚠️

Coding honesty trap: the "give me code that does X"

The bright line in CS: pasting an assignment description and asking for working code. CS faculty run AI-detection passes; they also know what beginning-student code looks like, and AI output looks different. Even if it weren't detectable, you don't learn to code by reading code somebody else wrote. The two prompts above keep your hands on the keyboard. If your school's CS department has an explicit AI-tools policy (most do now), read it before any of these prompts: some courses ban even the "explain my error" prompt, and the M4.2 conversation with the prof is the right move there.

Pair this with Lesson 3.3

This page is the long version of the subject-tweaks panel in Lesson 3.3:The Active Recall Engine. The lesson covers why active recall works in every subject; this page covers how to tune it per class. Together they're the full active-recall picture.

Back to the curriculum

Save this page. Come back at the start of every term: pick the playbook for each class, paste the prompts, fill in the brackets, drill.

Back to the curriculum →