Template library: reusable prompts

Template library: reusable prompts

Why it matters: A template library saves time and makes quality repeatable.

Goals

• Create 3 reusable prompt templates.
• Define when to use each template.
• Add a minimal QA block to each template.

Key definitions

• Template: A reusable prompt structure with placeholders and rules.
• Placeholder: A variable you fill in (audience, constraints, examples, source text).
• Default: The safe baseline behavior when inputs are missing.

Workflow (step-by-step)

1. Pick 3 recurring tasks (summary, rewrite, outline, FAQ, email).
2. For each task, write a template: context → task → constraints → checklist → QA.
3. Add placeholders: {audience}, {tone}, {length}, {source}, {constraints}.
4. Add a QA mini-step: “list uncertainties + what to verify”.
5. Store templates in one place and use them for 7 days.

Example (good vs bad)

✅ Good: Templates reduce rework because they encode constraints and QA by default.

❌ Bad: You re-invent prompts each time and forget critical constraints.

Checklist

• Templates have placeholders.
• Templates include QA.
• Templates are named and searchable.
• Templates are tested on real tasks.

Metrics / criteria

• Time saved: fewer edits per output.
• Consistency: outputs follow the same structure.
• 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: Templates too long to use. Fix: Keep a short “core” plus optional advanced blocks.
• 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 template library: reusable prompts.
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/