Rewrite and tone shift

Rewrite and tone shift

Why it matters: Rewrites should change meaning only when you intend to, and tone should match audience.

Goals

• Perform a tone shift without changing meaning.
• Preserve facts and constraints.
• Use a checklist for style.

Key definitions

• Tone: Voice/style (formal, friendly, direct) that affects how content is received.
• Semantics: Meaning: facts, claims, commitments, and constraints.
• Style guide: Rules for words, sentence length, and formatting.

Workflow (step-by-step)

1. Extract key facts/commitments (do not change these).
2. Define target tone + audience.
3. Rewrite with the tone constraints.
4. Run a “meaning diff”: list what changed in content (should be none unless requested).
5. Run QA: check facts, numbers, and policy statements.

Example (good vs bad)

✅ Good: A rewrite that changes tone while keeping the same commitments and facts.

❌ Bad: A rewrite that adds new claims or changes commitments accidentally.

Checklist

• Facts preserved.
• Tone matches audience.
• Meaning diff checked.
• No new claims introduced.

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.
• Meaning drift: 0 unintended changes.

Common mistakes + fixes

• Pitfall: Accidental meaning drift. Fix: Extract facts first and re-check after rewrite.
• 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 rewrite and tone shift.
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/