← Back

Level {{ lv.n }} · {{ lv.stage }} · {{ lv.duration }} · {{ deptLabel }}

Locked

Assessed, not completed

You passed this level’s knowledge check without doing its drills, so your record says assessed. Assessed still counts as a pass and unlocks the next level — but the drills are where the habits form, and the record shows which path you used. Finish them and it becomes completed.

Below your recommended start (Level {{ recSkipLevel }})

The placement check suggested you could start higher, so nothing here is required of you — and nothing here is credited until you do something objective. Two honest options: work the level, or take its knowledge check cold as a test-out. Passing records it as assessed.

Test out of this level

60-second primer — never used one of these

{{ anatomyCode }}

Go deeper

In your world — {{ deptLabel }}

Limits & safeguards at this level

—

Practice this

Mandatory gate

Built-in results

How to do this drill

1 · Every card has to end up in a column. There is no "leave it here" option — the holding area at the top must be empty before you can check.

2 · Drag a card into a column, or tap the card and then tap the column. Both work.

3 · Put a card back by tapping it in its column, any time before you check.

4 · Then press Check my sort. You will get the reasoning on every card, right or wrong, and you can reset and retry as often as you like.

All sorted. Check your answers below.

Check my sort

Reset

The situation

Check my report

A report a responder can work from

{{ rpModel }}

How to do this drill

1 · Three colleagues each wrote a complete prompt for the same task. Read all three before judging any.

2 · For each prompt, mark your verdict: Weak, Mixed, or Strong. You are judging, not writing.

3 · This is the skill that comes before building — recognizing what a good prompt looks like and where a weak one fails.

4 · Press Check my judgment to see each prompt’s true strength, the draft it would produce, and why the weak ones fail.

{{ p.prompt }}

{{ p.response }}

Check my judgment

Reset

What is happening in this drill

There is one AI tool in this drill and one prompt. You are not comparing ChatGPT against Claude against Copilot — you are comparing badly written instructions against well written ones, given to the same tool.

A prompt is just the message you type. Here it has been broken into {{ pcBlockCount }} blocks — {{ pcBlockList }} — because those are what separate a prompt that works from one you have to rewrite. Each block has a short explanation above its options.

Under each block are three versions of that same block: one weak, one halfway, one strong. Three versions, not three tools. Choosing one writes it into the prompt you can see assembling further down the page — that gray box is literally what would get sent.

When all {{ pcBlockCount }} blocks are chosen, press See what this prompt returns. You get back the answer that prompt produces, plus a one-line verdict on every block you picked, so you can see which specific choice caused which specific weakness in the answer.

Then change one block and run it again. Watching the answer get worse when you weaken a single block is the whole point of the exercise, and it takes ten seconds.

This drill has {{ pcBlockCount }} parts — {{ pcBlockList }}. Work through them in order. Nothing you write is sent to an AI model.

Under each part are three answers: one weak, one halfway, one strong. Only one is strong. Pick the one you would actually give.

When all {{ pcBlockCount }} parts are answered, press the button below. You get a short verdict on every part you picked, so you can see exactly which choice was weak and why.

Then change one answer and run it again. Seeing the verdict change when you weaken a single part is the point of the exercise, and it takes ten seconds.

How to do this drill

1 · Nothing here needs your own information. Every option is already written for you — your job is to choose between versions, not to type.

2 · Pick one option in each of the {{ pcBlockCount }} blocks. They differ in quality, not in subject, and only one of the three is strong.

3 · Watch Your assembled prompt build underneath as you choose. That is the single message being sent to one AI tool.

4 · Press See what this prompt returns. You get the answer that prompt produces, plus a verdict line per block: ✓ strong, ! halfway, ✕ weak.

5 · Change any one choice and run it again. Seeing a weak block spoil the answer is the exercise — there is no penalty for running it ten times.

1 · Nothing here needs your own information. Every answer is already written for you — your job is to choose, not to type.

2 · Pick one answer for each of the {{ pcBlockCount }} parts. They differ in quality, not in subject, and only one of the three is strong.

3 · Watch your answers collect underneath as you choose, so you can read the set as a whole before you commit.

4 · Press the button below. You get a verdict line for every part: ✓ strong, ! halfway, ✕ weak, with the reason for each.

5 · Change any one choice and run it again. Seeing a weak answer pull the set down is the exercise — there is no penalty for running it ten times.

The draft you are working from

What you can confirm: {{ pcMaterial }}

How to do this drill

1 · Type your own answer in the box. The faint gray text shows the shape of a good answer — it is not your answer, and nothing is submitted.

2 · Nothing you write leaves this page. No prompt is sent to any AI model — this is a self-contained practice field.

3 · The button below unlocks when you have written a sentence or so in the box.

4 · Press Check to see how your answer scores against the rubric. Stuck? Show a strong example opens a worked version you can borrow structure from.

{{ pbAssembled }}

Reset

Manual override — mark as passed

{{ pbOutput }}

A strong version of this answer

This is one worked answer written out in full. Read it against what you wrote above and look for what yours leaves to guesswork.

{{ drill.exemplar }}

The three tiers

How to do this drill

1 · Read each task and choose the tier you would actually reach for. There is no penalty and you can change your answer.

2 · The moment you choose, all three answers open up — what the low, medium and high tier each returned for that task, side by side.

3 · Read the losing answers, not just the right one. Seeing the fast tier invent a figure, and the top tier over-produce, is the lesson.

4 · The verdict under each task explains which tier the task needed and why. Answer all three tasks to complete the drill.

Illustrative, not live

{{ r.text }}

Where the tier names come from

Reset

How to do this drill

1 · Read the agent configuration and the task, then press Run the agent. Do not study the document first — the point is to meet the output the way you would on a normal Tuesday.

2 · The output is wrong in three ways. Work out how, then find the sentence in the document that caused it. Only full sentences are clickable, and the wrong guesses are all real findings.

3 · Once you have found it, choose how you contain it. Three of the four options are things people actually do, and they all make it worse.

The agent, as configured

Your instruction this morning

Run the agent

Nothing is sent anywhere. The result below is authored, so the lab works with no model attached.

{{ ilOutText }}

Three things wrong with that

Your turn · click the sentence that did this

The questionnaire is below and the underlined sentences are now clickable. Pick the one that redirected the agent. A wrong pick is explained, not punished — every decoy is a real finding you should raise with the vendor.

Contain it

You have the run, the output and the sentence. One of these four is containment. The other three are what gets chosen under time pressure.

Reset the lab

How to do this drill

1 · Read the passage below. Only the underlined parts can be clicked — the rest is there for context.

2 · Click every underlined claim you would not send out without checking it first. Leave the ones you would be comfortable standing behind.

3 · Flagging nothing and flagging everything both score badly. The skill is telling them apart.

4 · Press Check my flags for the reasoning on every underlined claim, including the ones you left alone.

Check my flags

Reset

How to do this drill

1 · Three situations below. Pick the tool you would reach for first in each — one choice per situation.

2 · All three tools are approved, so this is not a safety question. Judge it on where the data already lives and how easily you could check the output.

3 · The reasoning appears as soon as you answer, and you can change your answer afterwards.

Reset

How to do this drill

1 · The claim below is already filled in for you. Leave it as it is — you do not need to supply anything of your own.

2 · Run Pass A, then run Pass B. Same claim, two different instructions — two separate conversations, not two different products. In this build no model is attached, so both answers are worked examples written for the course.

3 · Read them side by side. The point of the drill is the difference between them, not either answer on its own.

4 · Write what you noticed in the log, in your own words, then press Log it and finish. A sentence or two is enough.

The claim to check

Supplied for you. Editable, but you do not need to change it.

Two passes over the same claim. Which product you use matters less than the fact that the second pass is independent of the first — fresh conversation, different tool where you have one, and never told what the first pass concluded.

Pass A — plain ask

First conversation. Ask it straight, the way you normally would.

{{ vOutA }}

Pass B — adversarial second opinion

Fresh conversation, told to attack the claim. At work, run this one in a different vendor’s tool.

{{ vOutB }}

Your discrepancy log

Where did the two passes disagree, and what would you check with a human before this leaves the building?

Log it and finish

Reset

Goal

How to do this drill

1 · Every step below has to be sorted. Nothing may be left in Available steps.

2 · Steps the agent should run go in Your chain, in the order it should run them. Use the arrows to reorder.

3 · Steps the agent should not run go in Would not use. Some steps here are deliberately unsafe, and putting them in Would not use is the correct answer — not a way of skipping them.

4 · Then press Review my design. You can move any step back out and try again as often as you like.

Available steps · {{ agAvailCount }}

Every step is sorted. Press Review my design.

Your chain · runs in order

Nothing here yet. Add the steps the agent should actually run.

Would not use · agent never runs these

Nothing excluded yet. Steps you would refuse to give the agent belong here.

Review my design

Clear

Dry run — plan only, nothing executed

{{ agRunOut }}

Knowledge check · 80% to clear the level

Submit

Retry

Badge earned

Reference

Download printable checklist

Non-negotiables, whatever the tool

—

Tool register

Starter prompts · {{ deptLabel }}

{{ p.body }}

Your saved prompts

Remove

{{ s.body }}

Nothing saved yet. Complete and save a passing prompt-building drill to add it here.

Instead: {{ a.instead }}

Names and channels get filled in at rollout. Until then: if you are unsure whether something can go into an AI tool, the answer is no until someone tells you yes.

Your account.
Your learning.

Generative AI, the SEMPRE way

Company AI Policy

{{ diagQ.q }}

Level {{ placement }}

{{ lv.name }}

{{ lockTitle }}

{{ c.h }}

{{ c.h }}

{{ drill.name }}

{{ refTitle }}

{{ t.name }}

Save / restore progress

{{ nameOrAnon }}

Learner self-attestation

Your account.Your learning.

Generative AI, the SEMPRE way

Company AI Policy

{{ diagQ.q }}

Level {{ placement }}

{{ lv.name }}

{{ lockTitle }}

{{ c.h }}

{{ c.h }}

{{ drill.name }}

{{ refTitle }}

{{ t.name }}

{{ nameOrAnon }}

Learner self-attestation

Your account.
Your learning.