Slides/briefs: from outline to draft

Slides/briefs: from outline to draft

Why it matters: Slides and briefs require strong structure and crisp wording.

Goals

• Create a slide storyboard.
• Draft speaker notes or brief text.
• Run a clarity check.

Key definitions

• Storyboard: Slide-by-slide plan with key message per slide.
• Key message: The single point the slide must communicate.
• Supporting points: Bullets/data that support the key message.

Workflow (step-by-step)

1. Define audience and decision context.
2. Create a 8–12 slide storyboard with key message per slide.
3. Draft bullets and one proof point per slide.
4. Draft speaker notes (optional) and tighten wording.
5. QA for clarity: each slide has one message.

Example (good vs bad)

✅ Good: A storyboard where each slide has one message and proof points.

❌ Bad: Slides with many ideas and no structure.

Checklist

• One message per slide.
• Proof points included.
• Wording tightened.
• Decision context clear.

Metrics / criteria

• Time to present reduced; clarity improved.
• Measurable: You can say whether the output is correct/complete (pass/fail or a score).
• Effort: You can produce the result in 15–30 minutes using the workflow.
• Clarity: Another person can run your prompt and get a similar outcome.

Common mistakes + fixes

• Pitfall: Slides that are documents. Fix: Put detail in notes; keep slides crisp.
• Pitfall: Vague instructions. Fix: Add constraints, examples, and a success checklist.
• Pitfall: One-shot prompting. Fix: Iterate: draft → critique → revise → verify.
• Pitfall: No validation. Fix: Add QA steps, tests, and explicit “what counts as done”.

Student tasks

1. Apply the workflow to one real work task related to slides/briefs: from outline to draft.
2. Create a small artifact: prompt, checklist, rubric, table, draft, or decision note.
3. Run one quality check and record what changed after the check.
4. Write a 3-sentence reflection: what worked, what failed, and what you will reuse.

Useful external sources

• OpenAI prompt engineering guide: https://platform.openai.com/docs/guides/prompt-engineering — Prompt structure, iteration, constraints, and evaluation habits.
• NIST AI Risk Management Framework: https://www.nist.gov/itl/ai-risk-management-framework — Risk framing, governance language, and verification mindset.
• OWASP Top 10 for Large Language Model Applications: https://owasp.org/www-project-top-10-for-large-language-model-applications/ — Practical AI safety risks such as prompt injection, leakage, and insecure output handling.
• Google People + AI Guidebook: https://pair.withgoogle.com/guidebook/ — Human-centered AI design, user control, feedback, and failure modes.

Bibliography

• OpenAI prompt engineering guide. https://platform.openai.com/docs/guides/prompt-engineering
• NIST AI Risk Management Framework. https://www.nist.gov/itl/ai-risk-management-framework
• OWASP Top 10 for Large Language Model Applications. https://owasp.org/www-project-top-10-for-large-language-model-applications/
• Google People + AI Guidebook. https://pair.withgoogle.com/guidebook/