🤖 KI-Agenten & Workflows
Drawing App
Beispiel-Ausgaben
So antworten ChatGPT, Claude und Gemini typischerweise auf diesen Prompt:
I'll create a comprehensive drawing application for you! The HTML structure will include a canvas element with a sidebar for tools (brush, pencil, shapes, text, eraser) and a top toolbar for color selection, layer management, and file operations. The JavaScript will handle mouse events for drawing, implement a layer system using multiple canvas elements, maintain a history array for undo/redo, and include keyboard shortcuts like Ctrl+Z for undo. Would you like me to start with the HTML structure or focus on a specific feature first?
I can help you build this drawing application, though I should note that creating a fully-featured app like this is quite complex and would require substantial code across multiple files. I'll provide a foundation with the core canvas drawing logic, tool switching, and basic color selection, but features like layer blending modes and SVG export involve advanced techniques that may need refinement based on your specific browser compatibility needs. Would you like me to start with a minimal working version that we can iteratively enhance?
Here's a complete HTML5 drawing application with canvas-based rendering. The implementation uses event listeners for mouse/touch input, maintains drawing state in JavaScript objects, and leverages the Canvas 2D context API for rendering operations. Color management uses both HSL and hex values, layers are implemented as stacked canvas elements with CSS positioning, and export functionality uses canvas.toDataURL() and toBlob() methods for format conversion.
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).