Deine AI-Identität und dein AI-Team, portabel für jede AI-Plattform.
Anmelden Loslegen
Menü
Einen Agent of Me erstellen Stile erkunden Professionelle Agenten Community-Agents Leaderboard KI-News
KI-Plattformen Verzeichnis Model Matrix Vergleichen Welche KI sollte ich verwenden? Integrationsleitfäden OpenClaw einrichten Prompt Fit
Lernen & Tools Lernen Daten befragen Agent Builder API
Über Über uns Kontakt Haftungsausschlüsse
Anmelden Loslegen
Konto
Deine KI-Identität, portabel

Erstelle ein kostenloses Konto, um dein Profil aufzubauen. Standardmäßig privat. Nichts wird geteilt, es sei denn, du veröffentlichst es.

Loslegen Anmelden
Dunkelmodus

🧭 Geführte Ansicht
Neu bei Prompts, System Instructions, Context Windows, Tokens? Wir erklären jeden Begriff beim Stöbern verständlich. Dieselben Seiten, mit integrierter Hilfe.

⚡ Expertenansicht
Du weißt, wie Prompting funktioniert. Nur das Wesentliche, klar und kompakt, ohne zusätzliche Erklärungen. Das ist die Standardansicht.

Oberflächensprache

Prompt Foundations · Abschnitt 4/5, Controlling the Output

Lernziele
Tippe auf Weiter (oder nutze die Pfeiltasten), um eine Idee nach der anderen zu sehen. Kein Timer, das Quiz mit 5 Fragen wartet am Ende. Der ← oben beendet jederzeit; der Fortschritt bleibt erhalten.

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 Fragen, bei jedem Versuch frisch aus dem Pool gezogen. Bestehensgrenze 60 %. Unbegrenzte Wiederholungen.

Nächster Abschnitt: The Iteration Loop →
Den vollständigen Lektionstext lesen

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.

Konjunktur

Business AnalystChief of StaffExecutive AssistantM&A AnalystManagement ConsultantOperations AnalystProject ManagerRecruiter

Finanzen

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

Rechtliches

Contract Review AssistantLegal Due Diligence AssistantLegal Research AssistantParalegal

Marketing

Brand StrategistContent StrategistGEO AnalystMarketing StrategistSEO AnalystSales Strategist

Persönlich

Career CoachLearning TutorReflection AssistantResearch AssistantTravel PlannerWriting Assistant

Immobilien

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