Workshop contents
Session 1 · Layer 1
Prompt Engineering
Asking better questions
Three steps to working with AI: prepare, prompt, and polish. The facilitator introduces the framework, then demonstrates each level live.
Step 1 — Define your objective
Before writing a single prompt, answer four questions:
| Question | What it means |
|---|---|
| Outcome and output | What decision do you need to support, and what form should the deliverable take? |
| Audience | Who will see or act on this output? Their level of detail shapes your prompt. |
| Information to provide | What metrics, documents, or datasets must you feed the AI? It cannot use what it does not have. |
| Scope and limitations | What can AI do here, and where does human expertise need to take over? |
Skipping this step is the most common mistake. A well-defined objective is worth more than a clever prompt.
Step 2 — Build the prompt
A prompt is assembled from building blocks. Not every use case needs all of them — the specificity of your desired output determines which to include.
Building blocks
| Block | Purpose |
|---|---|
| Task description | Tell the AI what you want it to do. Be concise and direct. |
| Role | The perspective or expertise the AI should adopt for this task. |
| Boundaries | What to include, what to exclude, and where to stop. |
| Context | Background the AI needs to generate a relevant response. Narrows down the space of possible outputs. |
| Specific requirements | Format, length, structure, metrics to include, or standards to follow. |
| Reasoning | Ask the AI to explain its logic, show trade-offs, or justify its recommendation. |
Prompt types
Three levels of prompt structure. Each adds building blocks as the task demands more precision.
| Type | Building blocks | When to use |
|---|---|---|
| Basic | Task description + Context | Quick lookups, simple summaries, first-pass exploration |
| Focused | Task description + Role + Context + Specific requirements | Structured analysis, formatted reports, audience-specific outputs |
| Comprehensive | Task description + Role + Boundaries + Context + Specific requirements + Reasoning | Executive decisions, high-stakes recommendations, cross-functional work |
Prompting tip. Not every use case requires every building block. Start with what your output demands and add blocks only when the result falls short.
Live demonstration — the same question, three prompt levels
The facilitator now runs three prompts against the DataCo dataset. Each corresponds to a prompt type above.
Demo A — Basic prompt
Prompt type: Basic (task description + context)
Using the attached DataCo supply chain dataset, what are the top late delivery products?
What happens. The AI has the data, so it pulls real product names — but the output is an unstructured paragraph with no ranking, no percentages, and no clear takeaway. It mentions a few categories without explaining why they matter.
Would you take this to a board meeting?
Lesson. The AI has the data but no direction. A minimal prompt produces a minimal answer — real numbers buried in a shapeless paragraph that no executive can act on.
Demo B — Focused prompt
Prompt type: Focused (task description + role + context + specific requirements)
You are a supply chain analyst. Using the attached DataCo supply chain dataset, identify the top 10 product categories with the highest late delivery rate. Output a Markdown table with exactly three columns: Category Name, Total Order Lines, and Late Delivery Rate (%). Sort by late delivery rate descending.
What happens. The AI returns a ranked table with real numbers from the dataset. Lacrosse leads at 60.1%, followed by Pet Supplies, Cameras, Strength Training and Music; the tenth entry sits near 56%. It looks precise and actionable.
This looks useful. But is it a decision, or just a sorted list?
Lesson. A specific prompt produces specific numbers — but numbers are not insight. What the room does not yet see: every one of those ten categories sits within four points of the company average. The ranking is noise.
Demo C — Comprehensive prompt
Prompt type: Comprehensive (all six blocks: task description + role + boundaries + context + specific requirements + reasoning)
You are a supply chain analyst presenting to the CEO. Using the DataCo dataset, analyse late delivery patterns and produce: 1. Top 10 product categories by late delivery rate (% of order lines late) 2. For each: the total profit associated with late order lines 3. Compare late-delivery rates across shipping modes 4. One actionable recommendation per category to reduce delays Boundaries: base every finding on the dataset provided. Do not speculate beyond what the data supports. If a pattern is ambiguous, say so. Format as an executive summary with a table. Flag any category where late delivery rate exceeds 50% as CRITICAL. Keep it under 500 words. Before generating the table, think step-by-step in a brief paragraph about how the 50% threshold interacts with the baseline company average. Then apply the threshold exactly as given. For each recommendation, explain the reasoning: what evidence supports it, what trade-off is involved, and what would need to be true for it to work.
What happens. The AI returns a structured executive brief — prioritised, quantified, with per-category recommendations. Two things surface that no one expected.
- 49 of 50 categories are flagged CRITICAL — because the company-wide late rate is 54.8% and the threshold sits below it. The AI followed the instruction precisely. The result is useless precisely because it did.
- Item 3 uncovers the real story. First Class 95% late, Second Class 77%, Standard Class 38%. The premium shipping modes are the late ones — and this only appeared because the prompt happened to include a shipping-mode comparison.
Would you take this to the board now? And what would you still need before acting on it?
Lesson. Prompt structure matters — role, constraints, format, and reasoning direction produce a markedly better output. But this prompt applied a bad threshold flawlessly and found the one useful pattern by accident. Better instructions improve direction. They do not replace missing context or missing evidence.
Layer 1 debrief
Show all three outputs side by side. The gap is visible in seconds.
Key takeawayMost organisations never get past Demo A. The same AI and the same data produce radically different results depending on how the question is asked.
Facilitator guide — why the 50% threshold is a trap
The threshold in Demo C is deliberate. It is the moment that proves precise instructions do not compensate for flawed human logic or missing business context, so it is worth walking the room through slowly.
| The flawed human assumption | Flag any category above 50% late as CRITICAL. To an executive writing the prompt, 50% sounds like a reasonable bar for a severe problem. |
| The mathematical reality | The company-wide late rate is already 54.8%, and 49 of the 50 categories sit between 47.7% and 60.1%. The threshold was set below the average. |
| The useless output | The AI flags 49 of 50 categories as CRITICAL. When almost everything is critical, the categorisation cannot prioritise anything. |
How to explain it
- Highlight the literal execution. The AI did exactly what it was told. The prompt applied a bad threshold flawlessly, which proves the tool will confidently execute poor instructions.
- Ask the pivotal question. “Would you take this to the board now? And what would you still need before acting on it?”
- Deliver the core lesson. The comprehensive prompt structure — role, boundaries, reasoning — improved the formatting and direction of the answer. It could not replace missing context or missing evidence.
- Reveal the real insight. Point at the story the AI found by accident: the premium shipping modes are the delay drivers. First Class 95.3% late, Second Class 76.6%, against Standard Class at 38.1%.
If the AI refuses the threshold. The added “think step-by-step, then apply the threshold exactly as given” line makes the model announce the flaw before complying, which is the stronger demo. A model may still argue for a better threshold instead of applying it. If that happens, take the win: it is the same lesson from the other direction, and the follow-up is “good — now who at this company decides what the threshold should be?”
Step 3 — Polish and iterate
No first prompt is final. After reviewing the output, refine with follow-up prompts: ask the AI to add what is missing, go deeper on a specific section, or change the format.
Then apply human expertise — check for accuracy, question the assumptions, verify the ethics, and make final edits before the output leaves your hands. AI drafts; you decide.
Prompting is iterative. You can always polish with a follow-up prompt. But the human must know the limitations of the tool, review every output, and own the final result.