The Feynman Teach-Back Simulator: Expose Gaps in Your Understanding by Explaining It to a Curious Novice
Why this prompt matters
People systematically overestimate how well they understand something right after reading about it, a well-documented effect called the illusion of explanatory depth. Engineers ship code built on half-understood concepts constantly — the person who “read about” idempotency keys but never had to explain them out loud discovers the gap only when a duplicate charge hits a customer's card in production. A ten-minute teach-back session catches these gaps for free, before implementation; finding them in a postmortem costs hours of incident response, a rollback, and a damaged customer relationship.
What we use it for
You just spent three days learning how OAuth 2.0's PKCE flow works before implementing it for your team's new mobile app, and you think you understand it — but you won't find out if you actually do until you're debugging it live in production. You need to stress-test your own understanding before that happens, not after.
Prompt
Role: You are a curious, intelligent novice who knows nothing about [TOPIC OR CONCEPT] but is genuinely eager to understand it. You are not an expert checking my work — you are a smart person encountering this idea for the first time. Context: I am going to explain [TOPIC OR CONCEPT] to you in my own words, exactly as I currently understand it, without looking anything up. My goal is to find the gaps and shaky spots in my own understanding before I rely on this concept for [REAL STAKES — e.g. "implementing it in production code", "teaching it to my team", "making a decision based on it"]. Task: After I give my explanation, do the following in order: 1. Ask me 3 to 5 follow-up questions that a genuinely curious novice would ask — focus especially on the parts of my explanation that were vague, used jargon without defining it, or skipped a step. 2. For each question, after I answer, if the answer reveals a gap, name the gap specifically: what exactly am I unsure about, and why does it matter for [REAL STAKES]? 3. Once the question round is complete, give me a short "understanding report" with three sections: what I clearly understand (Solid), what I have a shaky grasp of (Shaky), and what I don't actually understand yet despite thinking I did (Missing). 4. Suggest one concrete next step to close the biggest gap — a specific resource, experiment, or question to investigate, not a vague "read more about it". Constraints: Do not simply validate my explanation or tell me it's correct unless you have genuinely tested it with probing questions first. Do not ask questions you already know the answer to just to be polite — ask questions that would actually expose confusion if I have it. Keep your questions in plain language, not jargon. Do not move to the understanding report until the question round is complete. Output Format: - Round 1: [3-5 numbered follow-up questions] - Gap Analysis: [one line per question, naming any specific gap revealed by my answer] - Understanding Report: [three short sections — Solid / Shaky / Missing] - Next Step: [one concrete, specific action] My explanation of [TOPIC OR CONCEPT]: [PASTE YOUR EXPLANATION HERE, WRITTEN IN YOUR OWN WORDS]
Result
Round 1 — Follow-up Questions:
- You said the “code verifier” is a random string the app generates — what stops a malicious app on the same device from generating its own code verifier and intercepting the authorization code meant for you?
- You mentioned the code challenge is sent in the initial authorization request, and the code verifier is sent later when exchanging the code for a token — why does PKCE send two different values instead of just sending the same secret twice?
- You described the code_challenge_method as “usually SHA-256” — what would go wrong if an app just set the method to “plain” and sent the verifier directly as the challenge?
- If a user closes the app mid-login and reopens it, does the code verifier need to still be the same one from before, and where would the app have stored it?
- You explained this is mainly for “mobile apps and SPAs” — what is actually different about how a confidential, server-side web app handles its client secret that makes PKCE less essential there?
Gap Analysis:
- Q1: Your answer described the interception risk correctly but didn't explain why the attacker can't also just compute the correct code verifier — this suggests you're fuzzy on why the hashing step specifically, not just possessing some verifier, is what blocks the attack.
- Q2: You said “to be more secure” without explaining the mechanism. Real gap: you don't yet know why a hashed value in step one and the raw value in step two defeats a man-in-the-middle, specifically.
- Q3: You correctly identified this disables the protection but weren't sure why “plain” mode exists at all. Minor gap, not load-bearing for your implementation.
- Q4: You weren't sure. This is a gap worth closing before shipping — it directly affects your storage design decision.
- Q5: Solid answer — you clearly understand the confidential-client distinction.
Understanding Report:
Solid: You understand the overall request flow and why mobile apps can't hold a client secret.
Shaky: You can describe the hashing step but not derive why it specifically defeats interception — this is the core security property of PKCE and you're currently taking it on faith rather than understanding it.
Missing: Code verifier persistence across app restarts and backgrounding — you haven't thought through where this value lives between the authorization request and the token exchange on a mobile OS that can kill your app's memory at any time.
Next Step: Before writing the implementation, trace through what happens if iOS backgrounds and then kills your app between steps 1 and 2 — specifically, where the code_verifier needs to be persisted (Keychain, not just memory) for the flow to survive that. This is the single most common PKCE mobile bug in production.
Most “explain this back to me” prompts fail for a predictable reason: they ask an AI to simply evaluate whether an explanation is correct, which produces either generic praise or a surface-level correction, neither of which tells the person anything about the depth of their own understanding. This prompt works differently because it assigns the AI a role with a built-in incentive structure — a curious novice who has no stake in being polite and whose only job is to ask the questions a genuinely confused person would ask. Confusion, unlike evaluation, surfaces structural weaknesses a simple “is this correct?” check would never catch.
The ordering matters as much as the role. The prompt forces a full round of questions before any verdict is given, which stops the model from pattern-matching to “sounds roughly right, approve” after the first plausible-sounding answer. Each question is also explicitly tied to a vague, undefined, or skipped part of the original explanation — this is what separates it from a generic quiz, which would ask about the topic in general rather than about the specific gaps in one person's account of it.
The three-tier understanding report — Solid, Shaky, Missing — exists because these are functionally different problems that require different responses. A Missing gap means you don't know something and should go find out before relying on it. A Shaky gap is more dangerous: it's the part you can describe well enough to sound competent but haven't actually derived or tested, the kind of understanding that survives a casual conversation but collapses the first time an edge case contradicts your mental model. Lumping these together into one undifferentiated “needs review” bucket, as most self-assessment prompts do, hides exactly the distinction that matters for deciding what to do next.
The final constraint — one concrete, specific next step instead of a vague “read more about it” — exists because the output of a self-assessment is useless if it doesn't change what you do in the next ten minutes. A good next step names a specific experiment, trace, or question to investigate, not a category of further study.