BXUP Track progress & test yourself — free
AI at Office · Playbook · Foundation · ~4 min read
AI AT OFFICE · PLAYBOOK · FOUNDATION

Build a Personal Prompt Library for Your Role

You have already written your best prompts — then lost them in chat history. This playbook captures your ten most-repeated work prompts into a reusable, example-enriched library in Notion or a doc: the compounding asset that makes every other playbook a fifteen-second paste instead of a five-minute rewrite.

Workflow area: AI Fluency · Tier: Foundation · Hands-on time: ~30 minutes

The difference between someone who "uses AI sometimes" and someone visibly faster at their job is rarely prompting genius — it is that the second person never writes the same prompt twice. A prompt that produced a great weekly report once will do it again every week, forever, if you save it. This playbook is thirty minutes of setup that pays back every working day.

When to use — and when not to

  • Build it once you have repeatsyou have prompted the same kind of task three or more times: status updates, thread summaries, meeting minutes, formula help.
  • Build it per role, not per toolthe library follows your job. Prompts move between ChatGPT, Claude and Copilot with minor edits; your library should too.
  • Build it for your team when yours worksa shared library is how one person's good prompt becomes the department's standard.
  • Skip elaborate tooling on day onea prompt library in a system you never open is dead. Start in whatever you already check daily.
  • Skip saving one-off promptsa prompt you will never reuse is chat history, not a library entry. Save repeats and templates only.

The recipe

  1. Mine your own history. Open your ChatGPT/Claude/Copilot history and scroll the last two weeks. List every task you prompted more than once. Typical office top-ten: email from bullets, thread summary, tone rewrite, meeting minutes, status update, formula explanation, document summary, translation, agenda, job-ad or post rewrite.

  2. Pick a home with four fields. Notion database, OneNote page, Google Doc with headings — anything you open daily. Each entry gets: Name (what task), Prompt (paste-ready with [PLACEHOLDERS]), Example (one real input/output pair that worked), Notes (which tool, what to tweak).

  3. Convert your best chats into template entries. For each repeated task, find the chat where the output was actually good, and generalize it — or make the model do the generalizing:

    Below is a prompt I wrote and the output I liked. Turn my prompt
    into a reusable TEMPLATE:
    
    - Replace the specifics with [BRACKETED PLACEHOLDERS] and keep
      everything that made it work (the role, rules, format demands).
    - List the placeholders with a one-line hint for each.
    - Keep it under 150 words.
    
    My prompt:
    [PASTE YOUR PROMPT]
    
    The good output (for reference, do not template this):
    [PASTE THE OUTPUT]
    

    A finished entry looks like:

    NAME: Weekly status update
    PROMPT: Turn my work log into a status update for [AUDIENCE].
    Sections: Done / In progress / Blocked / Next week. Max 150 words.
    Flag risks explicitly. Do not invent progress — if the log is
    thin, the update is thin.
    Log: [PASTE LOG]
    EXAMPLE: (link to the chat that produced the good one)
    NOTES: Works in ChatGPT + Claude. For Copilot, add "use Teams
    messages from this week" instead of pasting the log.
    
  4. Enrich the big three with few-shot examples. For your three most-used prompts, paste one or two real, good outputs (your edited final versions, not the model's raw draft) into the template as "match the style and structure of this example." Few-shot examples are the single biggest quality lever you control — they carry your voice into every future output.

  5. Adopt the one-in rule. Every time a fresh prompt produces something great, spend sixty seconds templating it into the library before closing the tab. Once a month, delete entries you have not used — a ten-entry library you trust beats a fifty-entry junk drawer.

Make it yours

  • Notion: a database with Name, Prompt, Tool, Last-used and a Tag per workflow area — filterable, shareable with the team, and each entry's page holds the few-shot examples. Turn the best entries into a team-space "starter pack" for new joiners.
  • ChatGPT: promote your top prompts into Custom Instructions (style rules that apply everywhere) or a Project/custom GPT per workflow — the prompt stops being pasted at all. Keep the library as source of truth; tools change, your library survives.
  • Claude: use Projects with your templates and style samples in project knowledge — every chat in that project starts pre-loaded with your standards.
  • M365 Copilot: Copilot Prompt Gallery lets you save and share prompts inside the tenant — mirror your library's best entries there so they are one click away in Word and Outlook, and colleagues can reuse them.

Quality check

  • Every entry earns its placeused at least twice, or deleted at review.
  • Placeholders are self-explanatorysomeone else on your team could fill them without asking you.
  • Your three core prompts carry examplesfew-shot, from your own edited outputs, so the model imitates you and not the internet.
  • The library lives where you already lookif you have not opened it in a week, move it, do not rebuild it.
  • Nothing sensitive is baked intemplates contain placeholders, never real customer names, salaries or unreleased numbers.
Note

A prompt library is also a privacy control — templates with [CUSTOMER NAME] placeholders remind you to genericize before pasting. Write the placeholder, not the data, into every saved entry; pb-12 covers what must never be pasted at all.

Key Takeaway:

The library is the compounding asset: every playbook in this track ends with a reusable prompt, and this is where they live. Ten trusted templates, refreshed monthly, will outperform any amount of ad-hoc prompting skill.

This is the free reading view. Open BXUP to track your progress, run the hands-on labs, and prove it with original, exam-pattern assessments.
© Anvi Innovate · BXUP — Be Exponentially Upskilled · BXUP is an independent learning platform, not affiliated with or endorsed by AWS, Microsoft, Google, NVIDIA, IBM, Salesforce, Databricks, Oracle or Anthropic. All trademarks belong to their respective owners. · bxup.in