Data summarization: tables and simple calcs

Data summarization: tables and simple calcs

Why it matters: Small data work is safer when you keep calculations transparent and testable.

Goals

• Summarize a small table correctly.
• Do simple calculations with checks.
• Explain assumptions.

Key definitions

• Aggregation: Summarizing data (sum, average, count) by category.
• Sanity check: A quick test to catch obvious errors (totals, ranges, units).
• Assumption: A choice you make when data is missing or ambiguous.

Workflow (step-by-step)

1. Define the question you’re answering (one sentence).
2. Describe the data columns and units.
3. Compute totals/averages with clear formulas.
4. Run sanity checks (ranges, totals, duplicates).
5. Summarize findings + recommended action.

Example (good vs bad)

✅ Good: A table summary that includes calculations and sanity checks.

❌ Bad: A summary that guesses trends without showing numbers or checks.

Checklist

• Units stated.
• Formulas shown.
• Sanity checks included.
• Assumptions labeled.

Metrics / criteria

• Calculation correctness verified; no unit confusion.
• 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: Hidden math. Fix: Show formulas and intermediate totals.
• 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 data summarization: tables and simple calcs.
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/