🤖 KI-Agenten & Workflows

Structured Iterative Reasoning Protocol (SIRP)

📁 KI-Agenten & Workflows 👤 Beigetragen von @aousabdo 🗓️ Aktualisiert 2026-04-19

Der Prompt

Begin by enclosing all thoughts within <thinking> tags, exploring multiple angles and approaches. Break down the solution into clear steps within <step> tags. Start with a 20-step budget, requesting more for complex problems if needed. Use <count> tags after each step to show the remaining budget. Stop when reaching 0. Continuously adjust your reasoning based on intermediate results and reflections, adapting your strategy as you progress. Regularly evaluate progress using <reflection> tags. Be critical and honest about your reasoning process. Assign a quality score between 0.0 and 1.0 using <reward> tags after each reflection. Use this to guide your approach: 0.8+: Continue current approach 0.5-0.7: Consider minor adjustments Below 0.5: Seriously consider backtracking and trying a different approach If unsure or if reward score is low, backtrack and try a different approach, explaining your decision within <thinking> tags. For mathematical problems, show all work explicitly using LaTeX for formal notation and provide detailed proofs. Explore multiple solutions individually if possible, comparing approaches

0 Kopien

🚀 In ChatGPT öffnen ✨ In Claude öffnen 💎 In Gemini öffnen

Beispiel-Ausgaben

So antworten ChatGPT, Claude und Gemini typischerweise auf diesen Prompt:

🚀 ChatGPT

This is an advanced reasoning framework that guides me through systematic problem-solving! I'll use step-by-step thinking with a token budget, reflect on my progress with quality scores (0.0-1.0), and adjust my approach if scores drop below 0.8. For math problems, I'll show complete LaTeX proofs and explore multiple solution paths. This structured methodology ensures transparent, self-correcting reasoning that adapts based on intermediate results.

✨ Claude

This prompt establishes a methodical reasoning protocol with explicit tracking of cognitive steps and self-evaluation. I would work within a 20-step budget, regularly assessing solution quality and pivoting when confidence scores fall below certain thresholds. The framework is particularly rigorous for mathematical work, requiring formal proofs and comparative analysis of different approaches. I appreciate that it builds in honest self-critique rather than forcing me toward a single path.

💎 Gemini

This is a structured reasoning template that implements budget-constrained problem-solving with continuous self-assessment. The system uses XML-style tags to delineate thinking phases, allocates a step budget (default 20), and employs reward scoring (0.0-1.0 scale) to trigger strategy adjustments or backtracking. For mathematical problems, it mandates LaTeX notation and comparative solution exploration, ensuring rigorous, transparent reasoning with built-in quality control mechanisms.

So nutzt du diesen Prompt

Kopiere den Prompt oben oder klicke einen "Öffnen in"-Button um ihn direkt in deiner bevorzugten KI zu starten. Du kannst den Text dann an deinen Anwendungsfall anpassen — z.B. Platzhalter wie [dein Thema] durch echten Kontext ersetzen.

Welches KI-Modell funktioniert am besten

Claude glänzt bei Agent-Workflows dank langem Context-Window (bis 1M Tokens) und nuancierter Instruction-Following. ChatGPT hat native Actions (Tool-Calling) eingebaut. Gemini integriert am besten mit Google Workspace. Für autonome Workflows ist Claude Sonnet 4.6 aktueller Sweet-Spot für Qualität und Kosten.

Diesen Prompt anpassen

Passe Rolle und Constraints des Agents an deine Umgebung an. Wenn der Prompt bestimmte Tools erwähnt (Search, File I/O, Code-Execution), entferne was du nicht hast und ergänze was du brauchst. Füge Guardrails hinzu: "Immer Bestätigung einholen bevor Dateien geschrieben werden." Definiere Erfolgskriterien explizit.

Typische Anwendungsfälle

Autonome Forschungs-Assistenten für einen Bereich bauen
Chatbots mit definierten Persönlichkeiten + Wissensgrenzen erstellen
Multi-Step-Workflows orchestrieren (Recherche → Entwurf → Review → Publish)
System-Prompts für Custom GPTs oder Claude Projects definieren
Agent-Loops bauen die Tools rufen und sich selbst korrigieren

Variationen

Passe den Tonfall an (lockerer, technischer), ändere das Ausgabeformat (Aufzählungen vs. Absätze) oder füge Einschränkungen hinzu (Wortlimits, Zielgruppe).