Turn a vague request into a clear brief

Auteur: AILesson4 min de préparationTesté avec:ChatGPTClaudeGeminiRévisé: 2026-08-27

Réponse rapide

Expose missing decisions, constraints, and success criteria before work begins. Fournir: The original request, Known context. Résultat attendu: A structured brief plus the questions that still need answers.

1

Ajouter votre contexte

Votre texte reste dans ce navigateur. AILesson Prompts ne l’envoie ni à un modèle ni à un serveur.

2

Votre prompt

Les champs non remplis restent visibles sous forme d’espaces réservés, afin que vous puissiez quand même copier et modifier le prompt.

Turn the request below into a clear, executable brief.

Original request:
[request]

Known context:
[context]

Do not invent missing facts. Separate confirmed information from assumptions. Produce:
1. Objective
2. Target audience or user
3. Required deliverable
4. Constraints and non-goals
5. Success criteria
6. Decisions already made
7. The five highest-priority questions that must still be answered

End with a one-sentence definition of done.
Essayer dans le Playground
Privé par défautL’assemblage du prompt se fait localement dans votre navigateur. Évitez de placer des informations confidentielles dans un service d’IA, sauf si votre organisation l’autorise.

De l'entrée au résultat

Un exemple détaillé

Voyez comment un contexte concret transforme cette recette en résultat utilisable.

Entrée réelle

The original request
We need a better onboarding experience for the volunteer scheduling portal before the autumn intake.
Known context
The portal is used by new volunteers at a community food bank. The operations team can edit emails and help content but cannot change the account-creation flow this quarter. The autumn intake begins on 15 September. Support logs show that new volunteers often ask where to find their first shift, but no baseline completion data has been collected. One designer and one operations coordinator are available for two weeks.

Exemple de sortie

1. Objective

Help newly registered food-bank volunteers find and understand their first scheduled shift before the autumn intake begins.

2. Target user

Confirmed: new volunteers using the scheduling portal. Assumption requiring validation: volunteers who contact support represent the broader onboarding audience.

3. Required deliverable

A reviewable onboarding improvement package that the operations team can implement within two weeks, covering editable emails and help content. The exact formats and number of assets are not yet confirmed.

4. Constraints and non-goals

  • Deadline: ready before 15 September.
  • Capacity: one designer and one operations coordinator for two weeks.
  • Changes are limited to emails and help content.
  • Account-creation changes and a full portal redesign are out of scope.

5. Success criteria

Reduce confusion about finding the first shift. A measurable target and baseline are still missing; the team must choose a proxy such as related support requests or successful first-shift discovery.

6. Decisions already made

Target the autumn intake, use existing editable communication surfaces, and exclude account-creation changes.

7. Highest-priority questions

  1. Which email and help pages can be changed?
  2. What path should volunteers follow to find a first shift?
  3. Which support-log examples reveal the main confusion?
  4. What metric and baseline will define improvement?
  5. Who approves and publishes the final content?

Definition of done: The agreed email and help-content changes are approved, published before 15 September, and paired with a defined measure for first-shift discovery.

Pourquoi cela fonctionne

  1. 1

    It makes the model preserve uncertainty instead of silently filling gaps.

  2. 2

    The output structure turns discussion into a reviewable work artifact.

Vérifier le résultat

  • Are assumptions visibly separated from facts?

  • Could another person tell exactly when the task is done?

Utilisez-la en toute confiance

Questions fréquentes

Des réponses pratiques sur le bon moment pour utiliser cette recette, ce qu’il faut fournir et les cas où une vérification humaine reste nécessaire.

What should I prepare before using “Turn a vague request into a clear brief”?

For “Turn a vague request into a clear brief,” prepare The original request and Known context. Replace placeholders only with information you can verify. If a detail is unknown, preserve that uncertainty explicitly instead of asking the model to infer it.

When is the “Turn a vague request into a clear brief” result not ready to use?

The result is not ready if it does not yet deliver the stated outcome—A structured brief plus the questions that still need answers—from the supplied evidence, or if it relies on unresolved assumptions, missing approvals, or invented details. Use the checks as release gates: revise the source inputs or assign a named, authorized reviewer instead of polishing an unsupported output.

Which AI tools have recorded tests for “Turn a vague request into a clear brief”?

The published test record for “Turn a vague request into a clear brief” lists ChatGPT, Claude, and Gemini as of 2026-08-27. This confirms recorded runs, not guaranteed compatibility or identical results in later product versions. For another tool or version, keep every constraint visible and repeat the result checks before use.

Faites avancer votre travail