L1
·
Quiz
·
Lab
L2
·
Quiz
·
Lab
L3
·
Quiz
·
Lab
L4
·
Quiz
·
Lab
Module Test
Lesson 1 · Module 2

Vague vs. Specific: The Core Difference

Why the gap between what you ask and what you get is always about specificity.
What actually changes when you add more detail to a prompt?

When the Curiosity rover landed on Mars on August 6, 2012, NASA engineers at the Jet Propulsion Laboratory had spent years writing extraordinarily specific instructions. Every command sent to the rover specified exact coordinates, force measurements in newtons, timing windows to the millisecond. Nothing was left to interpretation. The rover could not ask a follow-up question. Vague instructions would have meant a $2.5 billion spacecraft sitting still — or worse.

AI language models face a similar problem in reverse: they receive your words and must infer everything you left unsaid. Unlike NASA engineers, most people never learn to write with that level of precision — until now.

The Specificity Spectrum

Every prompt sits somewhere on a spectrum from completely vague to richly specific. The position on that spectrum directly determines how useful the AI's response will be. This is not a matter of opinion — it is a measurable, reproducible effect.

In 2023, researchers at Stanford's Human-Centered AI group published findings showing that adding just three specific constraints to a prompt — audience, format, and goal — increased user satisfaction with AI responses by over 60%. The words themselves mattered less than whether they carried concrete information.

Vague
"Tell me about space" — gives AI almost nothing to work with; response will be unfocused and generic.
Better
"Explain how black holes form" — has a topic and a task, but no audience, length, or purpose.
Specific
"Explain how stellar-mass black holes form, in 3 bullet points, for a 10-year-old who just watched Interstellar." — AI has everything it needs.
Why Vague Prompts Fail

AI models are trained on billions of text samples. When you send a vague prompt, the model must choose which of thousands of possible interpretations to follow. It defaults to the statistical average — the most common answer to the most common version of your question. That average is rarely what you specifically need.

Think of it like a treasure map with no landmarks. "Go north and find the chest" could apply to every patch of ground on the planet. Add "walk exactly 40 paces north from the old oak at the park entrance" and suddenly you are digging in one specific spot. Specificity in prompts works the same way — it narrows the search space from infinite to useful.

Real Example · Google Search · 2001 vs. 2024

In 2001, Google's engineers noticed that one-word searches returned terrible results. Users who typed "jaguar" wanted either the car or the animal — the engine couldn't tell. By 2024, Google processes queries averaging 4.7 words, and internal satisfaction data shows longer, more specific queries produce dramatically better outcomes. The same principle governs AI chat: more context, better results.

The Treasure Hunt Game

In this module, we treat specificity as a treasure hunt. Each lesson gives you a new "clue ingredient" — a specific type of detail that makes your prompts more powerful. By the end, you will have a complete map: a set of ingredients you can add to any prompt to unlock the exact response you need.

The game has four rounds: understanding what vague looks like, learning the five specificity ingredients, practicing the before/after rewrite, and finally running live tests to see the difference yourself.

Core Idea

Specificity is not about using more words. It is about including the right information — the details that answer the questions the AI would ask if it could ask them. Every vague word in your prompt is an unanswered question that the AI must guess at.

Lesson 1 Quiz

Vague vs. Specific — check your understanding before the lab.
1. When you send a vague prompt, what does an AI language model typically do?
Correct. AI models choose the statistical average interpretation — which means generic, unfocused output when your prompt is vague.
Not quite. AI models don't stop or randomize — they fill the gap with the most common interpretation, which is rarely your specific need.
2. According to Stanford Human-Centered AI research cited in the lesson, what three constraints most improved user satisfaction?
Correct — audience, format, and goal were the three constraints that boosted satisfaction by over 60% in that research.
Those are useful details, but the research specifically identified audience, format, and goal as the high-impact trio.
3. The treasure hunt metaphor in this lesson compares specificity to:
Exactly right. Specific details act like landmarks — they shrink the search space from infinite to one precise location.
Re-read the treasure map analogy. The key idea is that landmarks (specific details) narrow the space from infinite to one exact spot.
4. Which of these is the MOST specific prompt?
Correct. That prompt specifies the task (rewrite), scope (opening paragraph), topic (climate), audience (skeptical adult), and constraint (30 words).
Compare all four options — the last one gives the AI a task, scope, topic, audience, and a measurable constraint. That combination is what makes it most specific.

Lab 1 · Spot the Vague

Send vague prompts and observe what happens. Then improve them.

Your Mission

This lab is about seeing the problem firsthand. Start by sending a deliberately vague prompt, then send a more specific version and compare the responses. The AI assistant will help you analyze the difference.

Try at least 3 exchanges. Suggested starting point:

Start vague: "Tell me something interesting." Then try: "Tell me one surprising fact about the human immune system, in one sentence, for a curious 12-year-old." Compare what you get.
Specificity Lab
L1 · Vague vs. Specific
Welcome to Lab 1! I'm here to help you see the difference between vague and specific prompts firsthand. Try sending a vague prompt first — like "Tell me something interesting" — then a more specific version of the same request. I'll help you notice what changed in the responses. Ready? Go ahead and type your first prompt!
Lesson 2 · Module 2

The Five Specificity Ingredients

A framework used by professional prompt engineers — and now by you.
What are the five key ingredients that make any prompt more specific?

When OpenAI prepared GPT-4 for public release in March 2023, internal red-team testers discovered a recurring pattern: the most problematic outputs — both too harmful and too useless — came from prompts that were missing the same categories of information. The testers began tagging prompts by what they lacked. The most common gaps were who the audience was, what format was needed, what the actual goal was, how long the response should be, and what tone was appropriate.

These five gaps became an informal checklist inside the team. External prompt engineering courses — including those from Anthropic, Google DeepMind, and Cohere — later codified similar frameworks. The specificity ingredients below are drawn directly from those published guides.

The Five Ingredients

Think of writing a prompt like cooking a recipe. A dish with one ingredient is edible but boring. Add five well-chosen ingredients and you get something memorable. Here are the five specificity ingredients:

① Audience

Who will read or use the response? Age, background, expertise level, and emotional state all matter.

e.g. "for a first-year nursing student who struggles with anatomy"
② Format

What shape should the answer take? Bullet list, essay, table, step-by-step instructions, dialogue, code?

e.g. "as a numbered list of exactly 5 steps"
③ Goal

What will the response be used for? To teach, persuade, entertain, summarize, compare, or create something?

e.g. "so I can convince my manager to approve the budget"
④ Length

How long should the response be? A single sentence, a paragraph, 200 words, a full page?

e.g. "in 3 sentences maximum"
⑤ Tone

What emotional register? Formal, casual, encouraging, urgent, neutral, playful, serious, empathetic?

e.g. "in a warm but professional tone, avoiding jargon"
How the Ingredients Work Together

You do not always need all five. A quick factual question might only need a length constraint. A sensitive email might prioritize tone and audience. The skill is knowing which ingredients your specific prompt is missing — that is where the quality gap lives.

In 2022, Anthropic published a guide for using Claude (their AI) that noted prompts with at least three of these five ingredients produced measurably more "on-target" responses — ones users accepted without editing. Prompts with zero or one ingredient led to users refining the response three or more times on average before it was useful.

Before & After

Before: "Write me an email about the project delay."
After: "Write a 3-paragraph professional email to my project stakeholders (senior managers who are not technical) explaining that the software launch is delayed by two weeks due to a third-party integration issue — tone should be calm and solution-focused, not apologetic."

The "after" version has all five ingredients. The "before" has none.

The Treasure Clue for This Lesson

Think of each of the five ingredients as a clue in the treasure hunt. Every clue you add moves you closer to the buried chest — the exact response you need. A prompt with zero clues leaves you wandering. A prompt with all five sends you directly to the X.

Quick Reference

A = Audience · F = Format · G = Goal · L = Length · T = Tone
Memory trick: "A Fine Goal Lasts Today" — Audience, Format, Goal, Length, Tone.

Lesson 2 Quiz

The Five Specificity Ingredients — test your recall.
1. Which of the five ingredients is missing from this prompt: "Explain photosynthesis in bullet points, casually, in about 100 words, so I can teach it to my class."
Correct. The prompt has Format (bullet points), Tone (casually), Length (100 words), and Goal (teach my class) — but it never specifies who the class is. A 6-year-old needs a very different explanation than a 16-year-old.
Look again. The prompt includes bullet points (Format), casual (Tone), 100 words (Length), and "teach my class" (Goal). What's never mentioned is WHO the class actually is — their age, background, or level. Audience is missing.
2. According to Anthropic's published guide, what was the average number of times users had to refine a response when prompts had zero or one specificity ingredient?
Correct — three or more refinements on average when key ingredients were missing.
The lesson notes that prompts with zero or one ingredient led to users refining the response three or more times on average.
3. The memory phrase "A Fine Goal Lasts Today" maps to which order of ingredients?
Exactly right — Audience, Format, Goal, Length, Tone.
Check the gold callout at the end of Lesson 2. A=Audience, F=Format, G=Goal, L=Length, T=Tone.
4. You need to write a prompt asking for help creating a birthday card message. Which version best uses the five ingredients?
Correct. That version has Tone (warm, slightly humorous), Audience (70-year-old grandmother, loves gardening), Length (2 short sentences), and Goal (make her smile when she reads it alone). All five ingredients are present.
Compare all options. Only the third option gives the AI audience details (70-year-old grandmother, gardening), format (2 sentences), tone, and a specific goal. The others leave too many gaps.

Lab 2 · Ingredient Hunt

Identify which of the five ingredients are missing from real prompts.

Your Mission

Practice diagnosing prompts. Send a prompt to the AI and ask it to identify which of the five ingredients (Audience, Format, Goal, Length, Tone) are present and which are missing. Then rewrite the prompt to include all five.

Try at least 3 exchanges. Start with one of these examples or use your own:

Try: "Analyze this prompt for me: 'Help me summarize this report.' Which of the five ingredients — Audience, Format, Goal, Length, Tone — are present? Which are missing? Then show me a rewritten version with all five."
Ingredient Hunt Lab
L2 · Five Ingredients
Welcome to Lab 2! I'm your ingredient-hunting partner. Give me any prompt — yours or one you make up — and ask me to identify which of the five specificity ingredients (Audience, Format, Goal, Length, Tone) are present or missing. Then I'll help you rewrite it with all five included. Let's go!
Lesson 3 · Module 2

The Before/After Rewrite

How professional writers, researchers, and developers transform weak prompts into powerful ones.
What does the rewriting process actually look like in practice?

When GitHub released Copilot in June 2021 — an AI coding assistant built on OpenAI's Codex — early users struggled to get useful code suggestions. A developer survey conducted by GitHub in early 2022 found that users who got the best results had developed a personal habit: they never sent their first instinct. Instead, they wrote a rough prompt, read it back, added context about the programming language, the function's purpose, the expected input/output format, and any edge cases to handle — then sent the revised version.

GitHub published these patterns in a guide called "How to write better prompts for GitHub Copilot" in September 2022. The core technique was the same rewrite loop: draft, identify what's missing, add it, send. That three-step loop is what this lesson teaches.

The Three-Step Rewrite Loop

Professional prompt engineers rarely get a great response on the first try — and they know it. The difference is that they have a reliable rewrite process rather than just trying again with slightly different words and hoping for the best.

The loop has three steps:

Step 1
Draft your instinct. Write what naturally comes to mind. Don't edit yet — just get the request out.
Step 2
Ask: what would the AI have to guess? Read your draft and identify every word or phrase where the AI could interpret it two different ways.
Step 3
Replace guesses with facts. Substitute each ambiguous element with a concrete detail from the five ingredients (Audience, Format, Goal, Length, Tone).
Worked Examples
Before (Draft) What AI Must Guess After (Rewritten)
"Write something about healthy eating." For whom? What format? How long? What aspect of healthy eating? What will it be used for? "Write a 5-bullet-point cheat sheet on reducing sugar intake, aimed at busy parents with no nutrition background, for printing and sticking on a fridge."
"Explain machine learning to me." What do I already know? How deep? What's my goal — casual curiosity or professional use? How long? "Explain what machine learning is in 3 sentences for someone who knows Excel but has never studied programming. Goal: I'm deciding whether to take an online ML course."
"Make this email better." 'Better' how? More formal? Shorter? More persuasive? Who is receiving it? "Revise this email to be more concise (under 100 words) and more persuasive. The recipient is a skeptical VP who values data. Keep a professional tone."
The "What Would It Have to Guess?" Test

The most powerful question you can ask about any prompt you write is: "What would the AI have to guess to answer this?" Every guess is a gap. Every gap is a place where the response might miss your actual need.

In 2023, Ethan Mollick — a Wharton professor who studies AI adoption — published research showing that workers who explicitly tested their prompts for hidden assumptions before sending them got better outcomes than those who iteratively refined responses after the fact. The upfront investment in a rewrite saved time overall.

Treasure Hunt Progress

You now have two clues: the five specificity ingredients, and the three-step rewrite loop. Together, they give you a method — not just a list of things to add, but a process for finding what's missing. The next lesson turns this into a live game you play against your own prompts.

Common Rewrite Mistakes

Adding length without adding specificity. "Write something about healthy eating for busy parents who are interested in reducing their sugar intake and want to learn more about nutrition in a way that is easy to understand" — this is longer but still vague. Length is not specificity. Concrete details are.

Rewriting tone when you need format. If the AI's response is well-written but structured wrong (an essay when you needed bullet points), tone editing won't help. Identify which ingredient is actually missing.

Adding context the AI doesn't need. Backstory and emotional context are sometimes useful for tone calibration, but they shouldn't replace the core five ingredients. Keep rewrites focused.

Lesson 3 Quiz

The Before/After Rewrite — check what you've learned.
1. What is Step 2 of the three-step rewrite loop?
Correct. Step 2 is identifying every place the AI would have to guess — those are your gaps to fill in Step 3.
Step 2 is specifically about identifying hidden assumptions — asking "what would the AI have to guess?" before you edit anything.
2. In the GitHub Copilot research mentioned in the lesson, what habit distinguished users who got the best code suggestions?
Exactly right. The best Copilot users systematically rewrote their first instinct before sending.
The lesson describes how top Copilot users developed the habit of not sending their first instinct — instead adding context about language, function purpose, and expected format.
3. Why is "adding more words" not the same as "adding specificity"?
Correct. The lesson gives an example of a long prompt that's still vague because the extra words are just more vague elaboration — no concrete ingredients added.
The lesson explicitly shows a long, wordy prompt that is still vague — the extra words didn't add any of the five concrete ingredients. Length ≠ specificity.
4. Ethan Mollick's 2023 research at Wharton found that workers who tested prompts for hidden assumptions before sending them:
Correct — upfront rewriting saved time overall by reducing the back-and-forth needed after the response arrived.
Mollick's research showed that upfront assumption-testing produced better outcomes AND saved time — the investment before sending paid off.

Lab 3 · The Rewrite Challenge

Practice the three-step rewrite loop with live AI feedback.

Your Mission

Use the three-step rewrite loop on real prompts. Send a before version, then ask the AI to help you identify what it had to guess, then send the rewritten version and compare results.

Try at least 3 exchanges. Start here:

Try: "Here's my draft prompt: 'Help me prepare for a job interview.' Walk me through the three-step rewrite loop — what would you have to guess? Then help me rewrite it with all five specificity ingredients."
Rewrite Challenge Lab
L3 · Before/After Loop
Welcome to Lab 3! I'm here to walk you through the three-step rewrite loop on real prompts. Give me a draft prompt — any topic — and I'll show you exactly what I'd have to guess if you sent it as-is. Then we'll rewrite it together using the five ingredients. Let's make your prompts precise!
Lesson 4 · Module 2

Putting It Together: Live Treasure Hunt

Use everything you've learned to run a complete specificity game — and win.
How do all five ingredients combine into a single, powerful prompt-writing habit?

In 2023, NHS England piloted AI-assisted clinical documentation tools across several hospital trusts. A recurring problem emerged in the first months: clinicians produced wildly inconsistent AI outputs from the same underlying tools. Investigation revealed that doctors who got useful summaries had learned — often informally from each other — to include patient age bracket, the document's purpose (referral vs. internal note), and the required length in their prompts. Those who hadn't learned these habits sent one-line prompts and got one-size-fits-all responses that required heavy editing.

NHS Digital subsequently issued informal guidance recommending that clinical staff treat AI prompting like filling in a patient intake form — every field exists for a reason, and leaving blanks creates downstream problems. The specificity framework was, in essence, their solution.

The Complete Treasure Hunt Map

You now have all four clues collected across this module. Here is the complete map:

Clue 1

Vague prompts force AI to guess. Every guess is a gap between what you need and what you get.

Ask yourself: "Is my prompt specific enough to have only one reasonable interpretation?"
Clue 2

The five ingredients fill the most common gaps: Audience, Format, Goal, Length, Tone.

Ask yourself: "Which of the five ingredients am I missing?"
Clue 3

The three-step rewrite loop (draft → identify guesses → replace with facts) is a repeatable process.

Ask yourself: "What would the AI have to guess if I sent this now?"
Clue 4

Specificity is a habit, not a one-time fix. Apply it to every important prompt before sending.

Ask yourself: "Is this the first thing I thought of, or is it what the AI actually needs?"
When You Need All Five vs. Just Some

Not every prompt needs all five ingredients. The key is knowing when to invoke each one:

Audience matters most when the complexity or vocabulary of the response needs to match a specific person. A response for a child and an expert on the same topic should be completely different.

Format matters most when you will use the output in a specific way — a report, a slide deck, a code file, a social post. If format is open, you can leave it out.

Goal matters most for persuasive, creative, or strategic tasks where the AI's output needs to serve a larger purpose beyond the prompt itself.

Length matters most when you have a constraint — a word limit, a time limit, a character count, a conversation budget.

Tone matters most for human-facing communication — emails, speeches, marketing copy, care messages — where emotional register affects the reader's response.

Real Pattern · Google Bard / Gemini Internal Testing · 2023

Google's internal testing of Bard (now Gemini) before its 2023 public launch found that test users who added even one well-chosen specificity ingredient to their first-draft prompt were three times less likely to abandon a conversation mid-task. The single most impactful ingredient was Format — telling the AI what shape the answer should take reduced confusion about whether the response was useful.

The X on the Map

The treasure you are hunting in this module is not a perfect prompt template. It is a flexible mental checklist — four questions you ask yourself before sending any important prompt:

1. Could this be interpreted two different ways? · 2. Which of A-F-G-L-T am I missing? · 3. What would the AI have to guess? · 4. Have I replaced the guesses with facts?

That checklist is the X. Every skilled AI user in every field — from NHS clinicians to GitHub developers to Wharton researchers — has arrived at some version of it. Now you have it too.

Module 2 Takeaway

Specificity is the single highest-leverage skill in prompt writing. It costs no extra technology, no special access, and no subscription upgrade. It costs only the habit of pausing before you send, and asking four questions. The AI you already have access to will produce dramatically better results the moment you start using it.

Lesson 4 Quiz

Putting It Together — confirm your complete picture.
1. In the NHS England pilot, what was the key difference between clinicians who got useful AI summaries and those who didn't?
Correct. The effective clinicians had learned — informally — to include specificity ingredients: age bracket (audience), document purpose (goal), and required length.
The lesson describes how effective clinicians had informally learned to include patient age bracket, document purpose, and length — three of the five specificity ingredients — in their prompts.
2. According to Google's internal Bard/Gemini testing, which specificity ingredient had the single largest impact on reducing abandoned conversations?
Correct — Format was the single most impactful ingredient, because telling AI what shape the answer should take reduced confusion about whether the response was useful.
The lesson notes that Format was the most impactful single ingredient — it immediately clarified whether the response was in the right shape for the user's needs.
3. Which ingredient matters MOST when writing a persuasive email to a senior executive?
Exactly right. For persuasive human-facing communication, Tone (how it feels to read) and Goal (what it needs to achieve) are both essential — and the lesson notes both matter most for such tasks.
Review the "When You Need All Five vs. Just Some" section. For persuasive, human-facing communication to a specific person, both Tone (emotional register) and Goal (what the communication must achieve) are critical.
4. The four-question mental checklist from Lesson 4 is BEST described as:
Correct — the checklist is explicitly described as a flexible mental habit applicable to any field and any important prompt, not a rigid template or advanced technique.
The lesson describes the checklist as a flexible habit used by skilled AI users across all fields — NHS clinicians, GitHub developers, Wharton researchers. It's not rigid, professional-only, or advanced-only.

Lab 4 · Full Treasure Hunt

Apply the complete framework: four questions, five ingredients, one powerful prompt.

Your Mission

Run the full process end-to-end. Pick a real task you actually want help with — anything. Write a first-instinct prompt, then apply the four-question checklist, rewrite it with all five ingredients, and send both versions. The AI will help you analyze the difference in results.

Try at least 3 exchanges. Start here:

Try: "I'm going to run the full treasure hunt on a real task. My first-instinct prompt is: 'Help me plan a trip.' Walk me through the four questions, identify which ingredients I'm missing, help me rewrite it, then show me what a great response would look like."
Full Treasure Hunt Lab
L4 · Complete Framework
Welcome to Lab 4 — the full treasure hunt! Bring me any real task you want help with. Give me your first-instinct prompt and I'll walk you through all four checklist questions: Is it open to multiple interpretations? Which of the five ingredients are missing? What would I have to guess? What facts should replace the guesses? Then we'll rewrite it together and see the difference. What's your task?

Module 2 Test

15 questions · Score 80% or higher to pass · Be Specific: A Treasure Hunt Game
1. What is the primary reason vague prompts produce generic AI responses?
Correct. Without constraints, AI models pick the most statistically common interpretation — which is the average, not your specific need.
AI models default to the statistical average interpretation of a vague prompt — they fill the gap with the most common answer to the most common version of your question.
2. Which of these pairs represents the correct first and last steps of the three-step rewrite loop?
Correct. Step 1 is draft your instinct; Step 3 is replace guesses with concrete facts. Step 2 in between is identifying what the AI would have to guess.
The three-step loop: (1) Draft your instinct, (2) Ask what the AI would have to guess, (3) Replace guesses with concrete facts.
3. "A Fine Goal Lasts Today" is a memory device for:
Correct — A=Audience, F=Format, G=Goal, L=Length, T=Tone.
"A Fine Goal Lasts Today" maps to the five ingredients: Audience, Format, Goal, Length, Tone.
4. Which specificity ingredient matters most for a message that needs to affect someone emotionally — like a condolence note or a motivational speech?
Correct. Tone governs the emotional register — how the message feels to read — which is the critical variable in emotionally charged human-facing communication.
Tone matters most for human-facing communication where emotional register affects the reader's response — like condolence notes or motivational speeches.
5. The NASA Curiosity rover example in Lesson 1 illustrates:
Correct. The rover cannot ask follow-up questions — so commands must be exact. AI models face the same challenge in reverse: they receive your words and must infer everything left unsaid.
The Curiosity example shows that systems which can't ask follow-up questions require precise instructions — AI faces the same situation with vague prompts.
6. Which prompt best uses the Audience ingredient?
Correct. That version specifies age (8-year-old), prior knowledge (just learned about planets), curiosity level, and a constraint (easily confused by math) — rich audience detail.
Audience means specifying who will receive the answer — age, knowledge level, emotional state. Only the third option gives all of those details.
7. Stanford Human-Centered AI research found that adding the three most impactful constraints increased user satisfaction by over:
Correct — over 60% improvement in satisfaction from adding just three concrete constraints to a prompt.
The lesson cites Stanford Human-Centered AI research showing satisfaction increased by over 60% when three key constraints were added.
8. In the NHS England pilot, NHS Digital's informal guidance recommended that clinical staff treat AI prompting like:
Correct — the intake form analogy captures why each specificity ingredient matters: every field has a purpose, and missing fields cause problems downstream.
NHS Digital's guidance used the patient intake form analogy — every field exists for a reason, and leaving blanks creates downstream problems.
9. Which is an example of a common rewrite mistake identified in Lesson 3?
Correct. Lesson 3 explicitly warns: longer prompts can still be vague if the extra words are just more vague elaboration instead of concrete specifics.
Lesson 3's "Common Rewrite Mistakes" section specifically warns against adding length without adding specificity — more words that are still vague don't help.
10. The Format ingredient is LEAST important when:
Correct. Lesson 4 notes that Format matters most when you will use the output in a specific way. If format is open, you can leave that ingredient out.
The lesson states Format matters most when output will be used in a specific form (code, slide deck, handout). When format is open — any structure works — that ingredient is less critical.
11. Which prompt demonstrates the Goal ingredient most clearly?
Correct. The Goal ingredient is "so I can quickly decide whether it's worth reading in full before a board meeting in 20 minutes" — a specific purpose for the response.
The Goal ingredient answers: what will this response be used for? Only the third option tells the AI what the summary is for — making a time-pressured decision before a meeting.
12. GitHub Copilot's best users shared what specific habit that improved their results?
Correct. GitHub's 2022 guide documented that the best Copilot users consistently rewrote their first instinct to add context, purpose, and format before sending.
The GitHub 2022 guide documented that top users never sent their first instinct — they systematically added programming language, function purpose, input/output format, and edge cases before sending.
13. Google's internal Bard/Gemini testing found that adding one specificity ingredient made users three times less likely to abandon a conversation. That ingredient was:
Correct — Format was the single most impactful ingredient because it immediately reduced confusion about whether the response was useful.
Lesson 4's callout from Google's internal testing identifies Format as the ingredient that most reduced abandoned conversations — it clarified whether the response was in the right shape.
14. The treasure hunt metaphor in this module compares adding specificity ingredients to:
Correct. Each specificity ingredient is a landmark — it shrinks the search space the AI must navigate to find your exact desired response.
The treasure map metaphor: landmarks (specificity ingredients) narrow the search space from infinite possibilities to one exact spot — the response you actually need.
15. The four-question mental checklist from Lesson 4 is described as something that skilled AI users in fields like clinical medicine, software development, and business research have:
Correct. The lesson's closing point is that professionals across fields have independently arrived at versions of this checklist — and now you have it as an explicit, learnable framework from the start.
The lesson's final point is that NHS clinicians, GitHub developers, and Wharton researchers all independently arrived at some version of this checklist through experience — you now have it as an explicit framework without needing to rediscover it.