🤖 AI Agents & Workflows
File System Indexer CLI
Example outputs
Here is what ChatGPT, Claude, and Gemini typically return for this 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.
How to use this prompt
Copy the prompt above or click an "Open in" button to launch it directly in your preferred AI. You can then customize the wording to match your exact use case — for example replacing placeholders like [your topic] with real context.
Which AI model works best
Claude excels at agent workflows thanks to its long context window (up to 1M tokens) and nuanced instruction-following. ChatGPT has native Actions (tool-calling) built in. Gemini integrates best with Google Workspace data. For autonomous workflows, Claude Sonnet 4.6 is the current sweet-spot for quality and cost.
How to customize this prompt
Adjust the agent's role and constraints to your environment. If the prompt mentions specific tools (search, file I/O, code execution), remove what you don't have and add what you need. Add guardrails: "Always ask for confirmation before writing files." Define success criteria explicitly.
Common use cases
- Building autonomous research assistants for a specific domain
- Creating chatbots with defined personalities and knowledge limits
- Orchestrating multi-step workflows (research → draft → review → publish)
- Defining system prompts for custom GPTs or Claude Projects
- Building agent loops that call tools and self-correct
Variations
Adapt the tone (more casual, more technical), change the output format (bullet points vs. paragraphs), or add constraints (word limits, target audience).