Lesson 18 · Advanced · 20 min
Building your team's prompt library
Build your team's prompt library: one card per prompt with variables, a sample output, known limits and an owner, stored in a shared Page.
- Goal
- You will be able to turn a proven prompt into a reusable card, with variables in brackets, a sample output and limits, and organise your team's library in a shared Page.
- Skills
- Frame
A prompt that works for you only works for the team if it is documented: what it does, what to replace, what the result looks like, where it fails. The team library is a set of short cards, one per prompt, with variables in brackets and a sample output, kept in a shared Page that everyone can read and improve. Start with five tested cards, not thirty.
1What a prompt card must contain
Microsoft sets the example with its prompt gallery, organised by role and by application. Its help page on writing a good prompt gives the structure: goal, context, source, expectations. A team library applies the same logic to your own tasks, with your vocabulary and your formats. It serves three purposes: reproducibility between colleagues, quality that is measured instead of felt, and handover to newcomers without re-explaining every prompt.
A card fits on one screen and has six headings:
Heading Content Name and version "Meeting-report v2", date of the last change Use case When to use it, when not to Full prompt The four ingredients; variable elements in brackets: [audience], [attached file] Sample output A fictional, complete result obtained with the prompt Known limits What fails: multilingual meetings, files without headers Owner Who answers questions and updates the card The card's prompt follows the rules of the course: instruction first, source last, a stated length, a rule for missing information, a proofreading instruction. The guides of the model publishers converge on the sample output. Anthropic recommends providing examples to stabilise a format. That example also serves as a reference for the user, who compares what they get with what they should get.
Where to store the library? Favor a shared Page that the team co-edits, hosted on SharePoint or OneDrive, or a document on the team site. Avoid relying on Copilot's memory. According to the September 2026 documentation, persistent memory targets the paid licence and remains strictly personal.
Every team card must respect data privacy. No card contains real or confidential data. Sensitive amounts, dates, and names of colleagues or clients are systematically replaced with bracketed variables.
Diagram "The team's prompt library"Diagram generated by AI and reviewed 2A meeting-minutes prompt that drifted in six months
A team of five has been sharing by email, for six months, the prompt that writes their meeting reports. Everyone has changed it their own way, and the reports no longer look alike.
Weak prompt, as it circulates:
Write the meeting report.Each colleague gets a different structure. Owners are invented when the notes give none, and lengths range from ten lines to two pages.
Strong prompt: Turn 1 (running the standardised card):
Name: Meeting-report v2 (10/09/2026). Owner: executive assistant. Use case: report of an internal meeting from raw notes. Do not use for a client appointment. Write the report of the [meeting name] meeting of [date] for [audience]. Format: three sections: "Decisions taken", "Actions" (one bullet = one action, one owner, one deadline), "Points in disagreement or open". 250 words maximum, neutral tone, in English. If an owner or deadline is missing from my notes, write "to be specified" instead of extrapolating. If no decision was taken on a point, mention it explicitly. Before delivering, proofread: every action must come textually from my notes. Notes: [pasted text]Strong prompt: Turn 2 (checking ambiguity and updating team documentation):
In the Actions section, the point on ERP migration has no assigned owner in my notes. Did you strictly apply the "to be specified" rule, or did you infer an owner from context? If the notes are ambiguous, confirm the rule to record in the "Known limits" section of our team card.Copilot confirms that it wrote "to be specified" without guessing an arbitrary owner, and suggests documenting shared ownership cases in the known limits.
What changes: the bracketed variables state exactly what to fill in. The sample output stabilises the format. The known limits prevent using the prompt outside its valid scope.
3Turn a weekly prompt into a documented card
Choose a prompt that you or a colleague rewrite every week: progress update, client follow-up, standard reply, monitoring. Here is the starting prompt:
"Do the project progress update from my notes."
Rewrite it as a full card with its six headings. Fill in the name, version, precise use case, complete prompt with bracketed variables, fictional sample output, known limits, and designated owner.
The composer below produces the card's prompt. Enable the boosters to use professional vocabulary and prevent invention. Have a colleague test the card without verbal guidance, or run it yourself after 24 hours. Place the validated card into your shared team Page.
Self-assessment grid: (a) the six headings are filled in and no real data appears; (b) the card was run without help, by a colleague or by you 24 hours later; (c) at least one limit comes from a real attempt.
4The card that travels without its use case
The "Overdue reminder v3" card has worked for six months in the accounts department. It writes a firm reminder, cites statutory business terms, and announces late fees. A retail subscriptions manager copies it to handle twenty overdue files. The letters threaten penalties that cannot legally apply to consumers, triggering immediate customer disputes.
The flaw is obvious: the card was designed for a single operational scope without documenting exclusions. Removed from its original context, the prompt applies commercial terms ill-suited to individuals.
To protect the library, always specify exclusions in the "Use case" section. Include the audience category as a mandatory variable. Record every edge-case failure in known limits and test variations on multiple cases before publishing. Rule to remember: a prompt card travels without its author, so context must travel inside the card.
5Quiz
Three questions, instant feedback. Each option comes with an explanation.
6Proof of mastery
Paste your complete card (name and version, use case, prompt with variables, fictional sample output, limits, owner), then the written feedback of the colleague who used it without your help and the answer they obtained. If you are learning alone, replace that feedback with your own run of the card 24 hours later, adding nothing from memory, and the list of the points you found missing.
Criteria
Going further
The executive assistant and human resources cards of the site's library are built on this model. The lesson Writing a good prompt: the four ingredients recalls the structure of every prompt, and Pages and Notebooks: keeping and sharing your work explains how to host the library.
Frequently asked questions
Can Copilot memorise our team prompts for us?
Do not count on it. Microsoft documents a memory feature for Microsoft 365 Copilot, but its inclusion in Copilot Chat without a licence is not guaranteed according to the documentation in force in September 2026, and a personal memory cannot be shared. The library lives in a document the team co-edits: a Page, or a file on your team site.
How many prompts do you need to start?
Three to five, chosen among the weekly tasks that several people do the same way: meeting report, follow-up, progress update, standard reply. A library of thirty cards nobody has reviewed is worth less than a library of five cards tested by a colleague.
Do you need a sample output in every card?
Yes. The guides of the model publishers converge: an example of the expected result stabilises the format better than a list of adjectives. The example also serves as a check for the user, who compares what they get with what they should get.