🤖 KI-Agenten & Workflows
File System Indexer CLI
Beispiel-Ausgaben
So antworten ChatGPT, Claude und Gemini typischerweise auf diesen Prompt:
I'll help you build a comprehensive file system indexer in Go. Here's a complete implementation featuring concurrent directory walking using goroutines and channels, SHA-256 checksum calculation for duplicate detection, a query parser supporting AND/OR/NOT operators with wildcard matching, and incremental indexing with a SQLite backend. The tool includes JSON/CSV export capabilities, real-time progress bars using a third-party library, and ANSI color-coded search result highlighting. Performance statistics track indexing speed, file counts, and memory usage across all CPU cores.
I can outline a Go-based file indexer, though I should note that production-quality full-text search is complex. The core architecture would use filepath.Walk with worker pools for concurrent processing, storing metadata in a local database (perhaps BoltDB or SQLite). For the query syntax, you'd need a lexer/parser for boolean expressions, and content indexing could leverage existing libraries like bleve. Keep in mind that checksum-based duplicate detection on large datasets requires careful memory management and potentially disk-based sorting for scalability.
A Go file system indexer can leverage the filepath.Walk function for directory traversal and sync.WaitGroup for concurrent processing across multiple goroutines. For checksums, crypto/sha256 provides efficient hashing to detect duplicates. The encoding/json and encoding/csv packages handle export formats natively. Consider using a library like bleve (inspired by Apache Lucene) for full-text search capabilities, which supports boolean queries and can index file contents efficiently with incremental updates.
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).