Concrete workplace scenario
A team lead asks: “Which prompt examples from this week are safe enough for the team to reuse?”
It sounds like you should share a list of prompts. The trap is that a reusable library needs evidence, limits, risk notes, and a manager decision ask.
Worked answer
Bad example first: a prompt list is not a reusable library
Weak example
“Here are some good prompts for customer replies, status updates, and handoffs.”
What goes wrong
The library has no decision ask, no risk limitation, no evidence source, and no D15 handoff.
Work-ready version: make the library decision-ready
Reusable case
Prompt with request, context, input, constraint, and format.
Risk limit
Where the prompt should not be reused.
Decision ask
What manager should approve, reject, or repair.
Quick decision check
The library must ask for a decision rule
A manager-facing prompt library must show evidence, limits, and the decision needed before reuse.
Reusable case
Prompt with request, context, input, constraint, and format.
Risk limit
Where the prompt should not be reused.
Decision ask
What manager should approve, reject, or repair.
Library handoff trace
This is the small visible work change from today. Keep it shallow, real, and reusable tomorrow.
Before / after: what changed in your work?
Use this contrast to check whether today changed the actual work result, not just the prompt wording.
Before learning
After learning
What AI-in-workflow means today
Build today's artifact rows
Complete three short fill-ins. Keep one real work item per row, and change the sample wording so it fits your work.
| No. | Prompt case | Evidence comes from | Business use | Evidence quality | Library status |
|---|---|---|---|---|---|
| 1 | |||||
| 2 | |||||
| 3 |
Repair one weak row
Use this pass to find the row that could confuse someone, create unsafe AI use, or fail as workplace evidence before you export.
Repair example
Weak row: Library note: here are good prompts for replies and updates.
Repair move: Add evidence source, risk limitation, manager decision ask, and D15 handoff.
Better row: Reusable case: manager update prompt with evidence source and output comparison; limit: not for customer promises; ask: approve after one repair; D15 focus: track metric and evidence needs.
Choose the row you would be comfortable showing to a manager. It should have a clear task, boundary, owner, and next action.
Choose the row most likely to fail, confuse someone, expose sensitive input, or need review.
Write the exact change. Sentence starter: The weak row is weak because ___. I will repair it by adding ___ before using AI.
Manager decision ask and D15 handoff
Pass / fix / stop standard
Do not present a prompt as reusable if it lacks request, context, input, constraint, output format, and comparison evidence.
Export artifact
This file is today’s work receipt. It should show what changed in your work habit, not just that you filled a table.
Before you export
- Does each case include evidence and limitation?
- Does the artifact ask for a manager decision?
- Does it name the D15 handoff or next evidence focus?
What this artifact proves: This file proves you can turn Week 2 prompt practice into a manager-readable reusable prompt case library.
Weak export: vague rows, no owner, no repair note, or no next-use line.
Good export: one clear work case, one boundary/rule, one repair note, and one tomorrow-use or manager-use line.
Click Generate Markdown to create boss_prompt_case_library.md.