Every exercise gives instant feedback and explains why it is right — no account, no API key.
Most exercises belong to a lesson; each one also works standalone from this page.
- Assemble a data-cleanup prompt
Intermediate · data cleanup · spreadsheets · verification — from “Clean up messy data”
- Assemble a document-extraction prompt
Intermediate · data extraction · verification — from “Extract data from documents”
- Assemble a spreadsheet-help prompt
Intermediate · spreadsheets · verification — from “Spreadsheets: describe, don't guess”
- Assemble a structured-output prompt
Intermediate · structured output — from “Structured output (JSON, simply)”
- Assemble a voice-matching email prompt
Beginner · email · prompting — from “Email that sounds like you”
- Assemble an action-table prompt
Beginner · meeting notes · structured output — from “Meeting notes to action items”
- Build the deck brief
Beginner · presentations · structuring · prompting — from “AI for presentations”
- Build the support reply
Intermediate · support · tone · prompting — from “Support replies that de-escalate”
- Build the template
Intermediate · prompting · templates · support — from “Prompt templates you actually reuse”
- Build your first image prompt
Beginner · ai images · prompting — from “Subject, scene, style”
- Check the number claim
Intermediate · verification · numeracy — from “Check the numbers”
- Which request matches how an LLM actually works?
Beginner · mental models · task fit — from “What an LLM actually does”
- Which prompt sets real boundaries?
Beginner · constraints — from “Add constraints”
- Which prompt carries the context?
Beginner · context — from “Give useful context”
- Which prompt shows instead of telling?
Intermediate · examples · few-shot — from “Examples and few-shot”
- Choose the input mode
Beginner · multimodal · capabilities — from “Multimodal AI: text, images, audio”
- Which prompt aims at a result?
Beginner · outcomes — from “Define the outcome”
- Choose the palette
Beginner · ai images · colour — from “Colour and mood”
- Choose the right coding task
Beginner · coding · evaluation — from “What AI can (and can't) do with code”
- Choose the sound delegation
Intermediate · judgment — from “When not to rely on AI”
- Choose the stronger follow-up
Beginner · iteration — from “Iterate from the output”
- Choose the uncertainty-asking prompt
Intermediate · prompting · verification — from “Ask for uncertainty”
- Which statement about tokens is accurate?
Beginner · costs and limits — from “Tokens, simply”
- Choose when search changes the answer
Beginner · research — from “Search vs generation”
- Which task fits a plain generative model?
Beginner · foundations · task fit — from “What generative AI is”
- Compare two meeting summaries
Beginner · summarizing — from “Summarize without losing meaning”
- Compare two replies and pick the one to ship
Intermediate · evaluation · verification — from “Evaluate before you ship”
- Set the frame deliberately
Intermediate · ai images · composition — from “Composition and framing”
- Diagnose the layer
Beginner · tool selection · mental models — from “Models vs products”
- Expect the variance
Beginner · working with AI — from “Why answers vary”
- Fix the boss email prompt
Beginner · clarity · instructions — from “Write clear instructions”
- Fix the cover letter prompt
Beginner · job search · writing · grounding — from “Job search: CVs and cover letters with AI”
- Fix the forgetting chat
Beginner · long input · context management — from “Context windows”
- Fix the material prompt
Intermediate · ai images · materials · prompting — from “Materials and texture”
- Fix the triage prompt
Intermediate · triage · structured output — from “Classify and triage text”
- Fix the unstructured summary
Beginner · format — from “Specify the format”
- Generation or editing — pick the mode
Beginner · ai images · task fit — from “How image generation works”
- Inspect the suspicious citations
Intermediate · verification — from “Inspect the citations”
- Judge the cross-check
Intermediate · verification · research — from “Cross-check AI answers”
- Judge the image series
Advanced · ai images · consistency · evaluation — from “Consistency across images”
- Judge the two plans
Beginner · workflows · process design · evaluation — from “Prompt vs workflow: when one ask isn't enough”
- Order the edit loop
Intermediate · ai images · iteration — from “Iterate and edit”
- Order the long-document process
Intermediate · long input — from “Work with long input”
- Order the tool call
Intermediate · tools · function calling — from “Tools and function calling, simply”
- Order the workflow map
Intermediate · workflows · process design — from “Map a workflow before you build it”
- Pick the camera description
Intermediate · ai images · camera — from “Camera angle and lens”
- Pick the constraint style
Intermediate · ai images · constraints · prompting — from “Negative constraints”
- Pick the right shape
Intermediate · agents · workflows — from “What an agent is (and isn't)”
- Pick the right tier
Beginner · tool selection · costs and limits — from “Fast vs reasoning models”
- Plan your usage before you start
Intermediate · judgment · privacy · verification — from “Using AI at work: judgment calls”
- Set the light
Intermediate · ai images · lighting · prompting — from “Lighting fundamentals”
- Spot the fabrication
Beginner · verification · hallucinations — from “Why AI makes things up (hallucinations)”
- Spot the injected instructions
Intermediate · security · verification — from “Prompt injection, simply”
- Spot the policy traps
Intermediate · privacy · policy — from “Does ChatGPT train on your data?”
- Spot the stale claims
Beginner · verification · research · freshness — from “Check dates and freshness”
- Spot the text trouble
Intermediate · ai images · verification — from “Text inside images”
- Spot the training myths
Intermediate · training · mental models — from “Training vs inference: what chats change”
- Spot the unsupported claims
Intermediate · verification — from “Find the unsupported claim”
- Spot the unsupported policy claims
Intermediate · grounding · verification — from “Ground responses in your sources”
- Spot what should not be pasted
Beginner · privacy · verification — from “What not to paste”
- Structure the status report
Intermediate · reports · structuring · evidence hygiene — from “Reports that hold up”
- Trace claims to their origin
Intermediate · research · verification — from “Primary vs secondary sources”
- Use the reference well
Intermediate · ai images · references — from “Style references, honestly”
- Vet the file-renaming script
Beginner · coding · verification — from “Describe, vet, never blind-run”