Working with tables and CSVs (small-scale)

Working with tables and CSVs (small-scale)

Why it matters: Working with tables/CSVs is safe when you keep assumptions explicit and outputs structured.

Goals

• Define schema/columns.
• Ask for calculations with checks.
• Output a clean summary table.

Key definitions

• Schema: Column names, types, and meanings.
• Row: One record/observation.
• Derived field: A value computed from other columns.

Workflow (step-by-step)

1. Describe the schema (columns + units).
2. Define the question and the desired output table.
3. Compute derived fields with formulas.
4. Check for missing values and outliers.
5. Summarize and propose actions.

Example (good vs bad)

✅ Good: A structured output with formulas and checks.

❌ Bad: A narrative summary with guessed numbers and no checks.

Checklist

• Schema stated.
• Formulas shown.
• Checks included.
• Output table is clean.

Metrics / criteria

• No silent assumptions; calculations verified.
• 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: Ambiguous columns. Fix: Ask for definitions and units before calculating.
• 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 working with tables and csvs (small-scale).
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/