Research helper: questions, not answers

Research helper: questions, not answers

Why it matters: Using AI as a research helper is safer when it asks questions and frames uncertainty.

Goals

• Generate clarifying questions.
• Form a research plan.
• Avoid fabricated facts.

Key definitions

• Clarifying question: A question that, if answered, changes what you should do.
• Research plan: A list of questions, sources, and steps to validate claims.
• Assumption: A belief you are using without proof; must be tested or labeled.

Workflow (step-by-step)

1. State the decision you need to make.
2. Ask the model for 10 clarifying questions.
3. Answer the top 3, then ask for a refined plan.
4. Ask for likely assumptions and how to test them.
5. Only then ask for a draft output with explicit uncertainty labels.

Example (good vs bad)

✅ Good: AI helps you structure inquiry and lists what must be verified.

❌ Bad: AI gives a confident answer with made-up facts and no research steps.

Checklist

• Questions come before answers.
• Assumptions labeled.
• Sources and verification steps listed.

Metrics / criteria

• Verification time decreases; fewer wrong facts slip through.
• 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: Letting AI “answer” uncertain questions. Fix: Force a questions-first workflow.
• 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 research helper: questions, not answers.
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/