Building FAQs and knowledge bases

Building FAQs and knowledge bases

Why it matters: FAQs and knowledge bases work when questions are real and answers are consistent and scoped.

Goals

• Generate real FAQs.
• Write scoped answers with examples.
• Add escalation rules.

Key definitions

• FAQ: A frequently asked question with a clear, scoped answer.
• Scope: What the answer covers and what it explicitly does not cover.
• Escalation: When to route to a human or a different system.

Workflow (step-by-step)

1. Collect real questions (support logs, team notes, sales calls).
2. Cluster questions into 5–10 themes.
3. Write answers with scope + steps + example.
4. Add “when to escalate” rules.
5. QA: consistency, tone, and policy.

Example (good vs bad)

✅ Good: FAQ answers are consistent, scoped, and include examples and escalation rules.

❌ Bad: FAQ answers are vague, contradictory, or overpromise.

Checklist

• Questions are real.
• Answers are scoped.
• Examples included.
• Escalation rules included.

Metrics / criteria

• Self-serve success rate improves; fewer repeat questions.
• 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: Inventing FAQs. Fix: Use real logs or interviews.
• 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 building faqs and knowledge bases.
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/