Drafting long-form with sections

Drafting long-form with sections

Why it matters: Long-form drafting works best when you draft section-by-section with constraints.

Goals

• Draft with sections.
• Add examples and transitions.
• Run a final QA checklist.

Key definitions

• Section contract: What a section must include: purpose, key points, examples, length.
• Transition: A sentence that connects sections and preserves logic.

Workflow (step-by-step)

1. Create a section outline with purpose per section.
2. Draft each section independently with a section contract.
3. Add one example per section (scenario or data point).
4. Add transitions and remove redundancy.
5. Run QA: clarity, correctness, and completeness.

Example (good vs bad)

✅ Good: A structured draft that reads coherently and includes examples and criteria.

❌ Bad: A long draft that rambles with repeated points and no examples.

Checklist

• Sections have purpose.
• Examples included.
• Transitions added.
• Final QA run.

Metrics / criteria

• 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.
• Structure: sections map to outline with no missing parts.

Common mistakes + fixes

• Pitfall: Drafting everything at once. Fix: Draft section-by-section with constraints.
• 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 drafting long-form with sections.
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/