Transforming formats: table, bullets, narrative

Transforming formats: table, bullets, narrative

Why it matters: Format transforms change how information is consumed without changing meaning.

Goals

• Convert formats reliably.
• Preserve meaning and constraints.
• Choose the right format for the audience.

Key definitions

• Format transform: Changing representation (bullets ↔ table ↔ narrative) while preserving meaning.
• Lossy transform: A transform that drops information; should be intentional.

Workflow (step-by-step)

1. Define the target format and why it’s needed.
2. Extract key facts/constraints (must be preserved).
3. Convert to the target format with consistent structure.
4. Run a “meaning diff”: list what got dropped/added.
5. Polish for readability (labels, headings, ordering).

Example (good vs bad)

✅ Good: A table that preserves all key constraints and decisions.

❌ Bad: A transform that loses critical details or changes meaning.

Checklist

• Target format stated.
• Meaning diff checked.
• No key facts lost.
• Output readable.

Metrics / criteria

• Meaning drift 0; readability 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: Accidental omission. Fix: Extract must-keep facts before transforming.
• 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 transforming formats: table, bullets, narrative.
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/