The Testing Academy · AI for QA Study guide
AI for QA · Plain-English notes

AI Fluency, explained like you are five

The same framework as the main guide, with the jargon taken out. Every one of the four Ds and all three modes gets a one-sentence definition, a story a child would follow, the way it usually goes wrong, and the QA version. If Delegation and Discernment keep sliding off your brain, start here and read the full guide after.

By Pramod Dutta, The Testing Academy. Companion notes to the AI Fluency study guide, written for the AI Tester Blueprint batches at The Testing Academy. The definitions are Anthropic's four competencies and three modes of AI interaction. The analogies and the failure modes are teaching aids written for this page, not Anthropic's, and are labelled as such so nothing here gets mistaken for course material.

01

How to read this page

This is the plain-English companion to the full AI Fluency guide. Same framework, no jargon.

Every section below has the same four parts, so you can skim whichever one you need:

Part What it gives you
In one line The actual definition, no analogy
Like you are five A story you will still remember next week
How it goes wrong The failure mode, which is what makes it stick
For a tester The same idea in your day job

The definitions are Anthropic's. The analogies are mine, written for this page as teaching aids. Do not quote the sandwich or the babysitter back at an exam; quote the definitions.

02

The whole thing in one breath

AI Fluency means working with AI in a way that is effective, efficient, ethical and safe. Those four words are the goal. Getting there takes four skills, the four Ds, and the course is careful to draw them as interconnected rather than sequential.

Delegation"should I even ask?" Description"did I say it clearly?" Discernment"is this any good?" Diligence"will I sign it?" Arrows point both ways on purpose: these are four sides of one act, not four stages you pass through. EffectiveEfficientEthicalSafe what all four are aiming at
Drawn the way the course draws it: a ring with a cross through it, because every D talks to every other.

A memory hook for the names: ask, say, check, sign. Delegation is the asking, Description is the saying, Discernment is the checking, Diligence is the signing. Use it to remember the four, but do not mistake it for a running order. Poor Description sends you back to Delegation, and Discernment often tells you the description was the problem. Every pair in that diagram has an arrow going both ways.

03

D1. Delegation

In one line. Deciding what work to do with AI and what to do yourself.

Like you are five. You have homework and a very fast friend. Some homework you have to do yourself, because the point is that you learn to add up. Some your friend can just do, like copying the list out neatly. And some you do together. Delegation is putting the homework into one of those three piles before you hand anything over.

How it goes wrong. People skip straight to typing. The question "should this be an AI job at all?" never gets asked, so AI ends up doing the one task you actually needed to understand yourself.

One task arrives. Which pile? Do it yourself "the point is that I learn it" Learning to add up. If a shortcut removes the reason for doing it, do it. Do it together "I need a second brain" Working out the answer. Most real work lives here, and most people skip it. Hand it over "I can check this in a glance" Copying the list out neatly. Safe when being wrong is obvious and cheap to fix. The pile is chosen before the prompt is typed. That choice is the whole skill.
Nothing here is about prompting. Delegation happens before any of that.

For a tester. Should AI write this test, or is reading the requirement carefully the actual job? Generating two hundred boilerplate assertions is pile three. Deciding what "logged in successfully" even means is pile one.

Delegation splits into three. The framework breaks each D into three parts, and for Delegation they are the three things you have to know before you can choose a pile:

Part Plain English The question
Problem awareness Know what you are actually trying to do "What does done look like, in my own words?"
Platform awareness Know what this tool is and is not good at "Is this even the kind of thing it can do well?"
Task delegation Split the work to suit both of you "Which bits are mine and which are its?"

Most bad delegation is a missing first row. You cannot decide whether to hand something over while you are still vague about what it is.

04

D2. Description

In one line. Communicating effectively with AI systems.

Like you are five. You ask someone to make you a sandwich. "Make me a sandwich" gets you a sandwich, maybe with butter you hate. "Cheese sandwich, no butter, cut into triangles, and I cannot eat nuts" gets you the sandwich you wanted. The other person is not a mind reader and cannot see inside your fridge.

How it goes wrong. You picture the result clearly in your head, describe about a third of it, and then feel let down by the answer. The gap was never in the model. It was in the third you left out.

"Make me a sandwich" what you said A sandwich. With butter. Technically correct, not what you meant "Cheese, no butter, cut in triangles, I cannot eat nuts" The sandwich you pictured context, constraint, and shape of the answer Nothing here is a clever trick. It is just saying more of it.
Three things move most of the distance: context, constraints, and what the answer should look like.

For a tester. "Write tests for login" is the first sandwich. The second one names the framework, the fixtures that already exist, the acceptance criteria, whether you want the negative cases, and whether assertions belong in the page object.

Description splits into three, and they are genuinely different things to say:

Part Plain English Sandwich version
Product What you want back "cheese, cut in triangles"
Process How you want it worked out "check the fridge before you start"
Performance How you want it to behave with you "tell me if we are out of bread, do not guess"

Almost everyone writes only the first row. Performance is the one people never think to ask for, and it is the one that changes a conversation most: say "challenge my assumptions" or "be brief" and you get a different collaborator, not just a different answer.

05

D3. Discernment

In one line. Evaluating AI outputs critically.

Like you are five. Your fast friend hands the homework back and the handwriting is beautiful. Neat, straight, lovely. That tells you nothing about whether the sums are right. You still have to check the sums.

How it goes wrong. Fluent writing reads like correct writing. AI output is always well presented, so if you judge by how confident it sounds you will approve wrong answers at a very high speed.

1. Does it look right? Neat, confident, well formatted. Always yes. Tells you nothing. 2. Is it right? Check the sums. Run the code. Follow the link and read it. 3. Right for me? Correct in general, and still wrong for this codebase. Most people stop after check one, because check one is the only free one. Checks two and three cost real attention, which is the entire point of them.
Beautiful handwriting is check one. It is also the check that never fails.

For a tester. The generated test passes. Does it pass because the feature works, or because it asserts something that could never fail? A green test that cannot go red is worse than no test, because now nobody looks at that area again.

Discernment splits into three, and it mirrors Description exactly, which is the neatest thing in the whole framework:

Part Plain English What you are looking for
Product Is the answer good? Wrong facts, missing cases, does not fit the question
Process Was the working sound? It got there by bad reasoning and landed on the right answer anyway
Performance Is it behaving usefully? Agreeing with everything, padding, drifting off what you asked

Product, process, performance in both. Whatever you failed to describe is usually what you now have to discern, which is why the two sit opposite each other on the diagram with an arrow going both ways.

06

D4. Diligence

In one line. Ensuring responsible AI collaboration.

Like you are five. If you hand in your friend's homework and it is wrong, the teacher does not tell your friend off. Your name is on the page. Diligence is checking it before you hand it in, and being honest when someone asks who helped.

How it goes wrong. Quietly. Nothing breaks at the moment you skip it. It breaks later, in front of other people, and by then the trail back to the decision has gone cold.

AI produced it no responsibility here You reviewed it or said you did You shipped it it is in main now Your name on it all of it, always Three things sit here: be open about what AI did, check before it ships, and stay answerable once it has. None of them transfer to the tool.
Responsibility is the one thing in the whole framework you cannot delegate.

For a tester. You approved the pull request. When that suite goes flaky at 2am, "the AI wrote it" is not an answer anyone accepts, and it should not be.

Diligence splits into three, spread across the whole life of the work:

Part Plain English When it happens
Creation Choose the tool and the way you use it thoughtfully Before
Transparency Be honest about AI's part with anyone who needs to know During
Deployment Check it, then vouch for it After

The middle row is the one people quietly skip, and it is the cheapest of the three. A line in the pull request costs nothing and is the whole of transparency.

07

The three modes, side by side

Now the other half. The four Ds are the skills. The three modes are how much rope you hand over.

Automation a vending machine One button, one snack. You watch it drop. Wrong? You know instantly, and it cost you one snack. Augmentation cooking together You taste, they stir, you say "more salt". You are in the kitchen the whole time. That is the cost. Agency briefing a babysitter Bedtime is 8. No sweets. Ring me if there is blood. Then you leave. You shaped the rules, not the actions. you watch everything nobody is watching supervision falls, blast radius grows
Same four Ds in all three. What changes is when you spend them.
08

Automation, in plain English

In one line. AI executes specific tasks based on your instructions.

Like you are five. A vending machine. You put in a coin, press B4, and out drops exactly that packet of crisps. One button, one thing, and you are standing right there watching it fall.

How it goes wrong. Rarely, and cheaply. That is the appeal. The real risk is doing it fifty times in a row and skipping the check somewhere around number twelve, because eleven were fine.

For a tester. "Convert this one Selenium test to Playwright." You read the diff, you run it, you move on.

09

Augmentation, in plain English

In one line. You and AI collaborate as creative thinking and task execution partners.

Like you are five. Cooking with a friend. Neither of you makes the whole meal. You taste it, they stir, you say it needs more salt, they adjust. You are both in the kitchen the entire time, and the meal is better than either of you would have made alone.

How it goes wrong. You stop tasting. The conversation keeps going, the answers keep arriving, and at some point you are skimming and nodding rather than thinking. It looks identical to working right up until the moment it does not.

For a tester. Designing the framework together: arguing about whether assertions belong in the page object, sketching the fixture, having your reasoning pushed back on. This is where most real work lives, and it is the mode people skip.

10

Agency, in plain English

In one line. You guide AI to work independently on your behalf, shaping its knowledge and behaviour rather than specific actions.

Like you are five. You are going out for the evening and a babysitter is coming. You cannot possibly list every single thing that might happen while you are gone. So instead you teach them the rules: bedtime is eight, no sweets after dinner, ring me if there is blood. Then you leave.

Notice what you did there. You never told them what to do. You told them how to decide.

How it goes wrong. Every gap in the briefing gets filled by someone else's judgement, over and over, while you are not in the room. And you find out afterwards, from what is left behind.

Automation and augmentation: you pick the actions you decide one action you check it Agency: you set the rules, it picks the actions you set the rules once, up front action you never sawaction you never sawaction you never saw Every one of them decided by the rules you wrote, applied to situations you did not imagine.
This is the difference people miss: in agency you are writing a policy, not a request.

For a tester. An agent that triages your nightly CI failures: reads the log, decides flaky or real, files or ignores. You never see most of those decisions. You see the rules you wrote and whatever it left behind.

The order that keeps people out of trouble: automation, then augmentation, then agency. The common mistake is jumping the middle one, because agency sounds like leverage. But augmentation is where you learn what good actually looks like for a task. Write the rules after you know that, not before.

11

One task, all four Ds

A concrete run through, so the loop is not abstract.

Step The question On a real QA task
Delegation Should AI do this? Two hundred API tests from an OpenAPI spec. Boilerplate, checkable, so yes. Deciding which endpoints matter is mine.
Description Did I say it properly? Name the framework, the auth fixture, the naming convention, and say I want the 4xx cases too, not just happy paths.
Discernment Is it any good? Run them. Then break the endpoint on purpose and confirm the tests actually go red. Green means nothing until you have seen red.
Diligence Will I sign it? Say in the PR that the suite was generated and how it was checked. Then own it when it flakes.

Try it yourself on the last thing you asked an AI to do. Which of the four did you skip? Almost everyone skips the same one twice: Discernment, because the answer looked finished. Whichever one you skipped is where your next hour of study goes, since your fluency is set by your weakest D and not your average.

12

The AI words you will hear

The course ships a terminology sheet. These are the same terms in my own words, with the bit that matters to a tester added.

Term In plain English
Generative AI AI that makes new things (text, code, images) instead of just sorting or scoring things that already exist.
Large language model (LLM) A generative model trained on an enormous amount of text so it can read and write language. Claude is one.
Parameters The billions of internal numbers a model adjusts during training. They are the model. Nobody hand-writes them.
Neural network Layers of connected nodes that learn patterns from examples. Loosely inspired by brains, not a copy of one.
Transformer The 2017 design that made modern LLMs possible, by letting the model weigh how every word relates to every other word rather than crawling left to right.
Scaling laws The observed pattern that bigger models with more data and compute keep getting better, and that new abilities show up at certain sizes without anyone programming them. An observation, not a law of nature.
Pre-training The first, huge phase where the model learns language and world knowledge from text.
Fine-tuning The follow-up phase that teaches it to follow instructions, be useful, and refuse harmful things.
Context window How much it can hold in mind at once: your conversation plus anything you pasted. There is a ceiling, and it differs by model.
Hallucination Being confidently wrong. The output is fluent and plausible and simply not true. This is the failure mode Discernment exists for.
Knowledge cutoff The date after which the model was not trained on anything. It does not know what happened later unless you tell it or it can look.
Reasoning models Models built to work through a problem in steps before answering, which helps on things that need actual logic.
Temperature A dial for randomness. Higher is more varied and more surprising, lower is more predictable and repeatable.
Retrieval augmented generation (RAG) Giving the model real documents to read at question time, so it answers from sources instead of memory. A direct countermeasure to hallucination.
Bias Systematic skew in outputs that favours or disadvantages some group, usually inherited from the training data.

Two of these matter more than the rest for testing work. Hallucination is why a confident answer is not evidence, and context window is why a model that was sharp ten messages ago starts dropping details: you have not made it worse, you have run out of room.

13

The prompting words you will hear

Term In plain English
Prompt Everything you send: the instruction plus anything you pasted along with it.
Prompt engineering Getting good at writing those. Mostly clear communication, with a few AI-specific tricks on top. This is Description with a job title.
Chain of thought Asking it to work through the steps rather than jump to an answer. Helps on anything with actual reasoning in it.
Few-shot (n-shot) Showing two or three worked examples of what you want instead of describing it. The "n" is how many examples. Often faster than explaining.
Role or persona Telling it who to be: "answer as a senior SDET reviewing this PR". Changes vocabulary, depth and what it thinks is worth mentioning.
Output constraints Saying the shape up front: how long, what format, which sections. This is the single cheapest fix for disappointing answers.
Think-first Asking for the reasoning before the conclusion, so you can check the working rather than only the verdict.

Notice that every row in that table is a Description technique. Prompt engineering is not a separate skill sitting next to the 4Ds, it is one of the four with a more marketable name. That is worth knowing before you pay for a course in it.

Where this came from, and the licence. The terminology list is Anthropic's, from the AI Fluency cheat sheet by Rick Dakan, Joseph Feller and Anthropic, released under CC BY-NC-SA 4.0. The definitions above are rewritten rather than reproduced, because that licence is non-commercial and this site sells courses. If you want the original wording, get it from the course itself at Anthropic Academy, which is free.

14

Where to go next