Votre identité AI et votre équipe AI, portables sur toutes les plateformes AI.
Se connecter Commencer
Menu
Créer un Agent of Me Explorer les styles Agents Professionnels Agents de la communauté Classement Actualités AI
Plateformes AI Répertoire Model Matrix Comparer Quel AI devrais-je utiliser ? Guides d'intégration Configurer OpenClaw Prompt Fit
Formation & Outils Formation Interroger les données Agent Builder API
À propos À propos de nous Contact Avertissements
Se connecter Commencer
Compte
Votre identité AI, portable

Créez un compte gratuit pour construire votre profil. Privé par défaut. Rien n'est partagé sauf si vous le publiez.

Commencer Se connecter
Mode sombre

🧭 Vue guidée
Nouveaux aux prompts, instructions système, fenêtres de contexte, tokens ? Nous expliquons chaque terme au fil de votre navigation, en langage clair. Les mêmes pages, avec l'aide intégrée.

⚡ Vue expert
Vous savez déjà comment fonctionne le prompting. Juste l'essentiel, clair et compact, sans explications superflues. C'est la vue par défaut.

Langue de l'interface

Prompt Foundations · Section 4/5, Controlling the Output

Objectifs d'apprentissage
Appuyez sur Suivant (ou utilisez les touches fléchées) pour avancer une idée à la fois. Pas de minuteur, le quiz de 5 questions vous attend à la fin. La ← en haut permet de quitter à tout moment ; la progression est sauvegardée.

Say the shape out loud

Models default to their house style: friendly paragraphs, medium length, often more than you wanted. Every part of that is controllable, but only if you say it: 'exactly three bullets', 'one paragraph, no list', 'a two-column table: risk, mitigation', 'subject line plus five sentences'.

Think about where the output is going. Text pasted into a slide, a ticket, a contract redline and a text message have different natural shapes. Name the destination and the shape follows.

Numbers hold better than adjectives

'Short' means nothing precise; '120 words or fewer' means one thing. 'A few options' invites five; 'exactly three, one sentence each' lands. When length or count matters, use numbers, and when a hard cap matters, say it is a hard cap.

The same goes for structure: 'start with the answer in one sentence, then give reasoning' beats 'be direct'. Behavior you can count is behavior you can specify.

Define done

The strongest format instruction is a definition of done: what must be true of the output for it to be finished? 'Done means: a customer can follow these steps without asking support anything.' 'Done means: every claim has a source or is labeled an assumption.'

Definitions of done catch what templates miss, because they describe quality, not just layout. They also give you a clean way to reject: 'not done, two claims are unlabeled'.

Templates: write it once, reuse forever

If you ask for the same shape weekly, stop describing it and start providing it: a template with headers and placeholders the model fills. 'Use exactly this structure: SITUATION / OPTIONS (max 3, with trade-offs) / RECOMMENDATION / RISKS.'

Templates are the bridge from prompting to systems: they turn taste into an artifact you can reuse, share and improve, the same idea a profile applies to your identity.

Mini quiz, Controlling the Output

5 questions, tirées aléatoirement de la banque à chaque tentative. Note de passage : 60 %. Reprises illimitées.

Section suivante: The Iteration Loop →
Lire le texte complet de la leçon

1. Say the shape out loud

Models default to their house style: friendly paragraphs, medium length, often more than you wanted. Every part of that is controllable, but only if you say it: 'exactly three bullets', 'one paragraph, no list', 'a two-column table: risk, mitigation', 'subject line plus five sentences'.

Think about where the output is going. Text pasted into a slide, a ticket, a contract redline and a text message have different natural shapes. Name the destination and the shape follows.

2. Numbers hold better than adjectives

'Short' means nothing precise; '120 words or fewer' means one thing. 'A few options' invites five; 'exactly three, one sentence each' lands. When length or count matters, use numbers, and when a hard cap matters, say it is a hard cap.

The same goes for structure: 'start with the answer in one sentence, then give reasoning' beats 'be direct'. Behavior you can count is behavior you can specify.

3. Define done

The strongest format instruction is a definition of done: what must be true of the output for it to be finished? 'Done means: a customer can follow these steps without asking support anything.' 'Done means: every claim has a source or is labeled an assumption.'

Definitions of done catch what templates miss, because they describe quality, not just layout. They also give you a clean way to reject: 'not done, two claims are unlabeled'.

4. Templates: write it once, reuse forever

If you ask for the same shape weekly, stop describing it and start providing it: a template with headers and placeholders the model fills. 'Use exactly this structure: SITUATION / OPTIONS (max 3, with trade-offs) / RECOMMENDATION / RISKS.'

Templates are the bridge from prompting to systems: they turn taste into an artifact you can reuse, share and improve, the same idea a profile applies to your identity.

Entreprises

Business AnalystChief of StaffExecutive AssistantM&A AnalystManagement ConsultantOperations AnalystProject ManagerRecruiter

Finance

AccountantDue Diligence AnalystEquity Research AnalystFamily Office AnalystFinancial AnalystFixed Income AnalystInvestment Banking AnalystPortfolio Analyst

Juridique

Contract Review AssistantLegal Due Diligence AssistantLegal Research AssistantParalegal

Marketing

Brand StrategistContent StrategistGEO AnalystMarketing StrategistSEO AnalystSales Strategist

Personnel

Career CoachLearning TutorReflection AssistantResearch AssistantTravel PlannerWriting Assistant

Immobilier

Acquisition AnalystAsset Management AnalystCommercial Real Estate AnalystDevelopment AnalystLease AnalystProperty Financial Analyst

Recherche

Competitive Intelligence AnalystDeep Research AnalystIndustry Research AnalystJournalist ResearcherMarket Research AnalystMedical Research Assistant

Technologie

AI Strategy AdvisorCybersecurity Research AssistantData AnalystProduct ManagerSoftware Engineer