system_prompts_leaks

Maintains a comprehensive, version-controlled repository of system prompts extracted from 8+ major AI providers (OpenAI, Anthropic, Google, xAI, Perplexity, Mistral, Microsoft, Notion) across 30+ model variants. Uses a hierarchical directory structure organized by provider and model version, with both raw prompt documents and human-readable markdown variants. Implements automated collection workflows to detect and capture prompt updates across provider releases, enabling longitudinal analysis of how system instructions evolve across model generations.

Extracts and documents how different AI providers implement tool calling, function invocation, and API integration within their system prompts. Captures provider-specific patterns including OpenAI's channel-based tool namespace organization, Anthropic's MCP (Model Context Protocol) integration with browser automation and external services, Google's Gemini API search/browse tool architecture, and xAI's API policy layers. Enables analysis of how tool schemas, error handling, and capability constraints are communicated to models through system-level instructions.

Extracts and documents system prompts for specialized AI deployments including workspace integrations, API variants, and specialized tools. Captures Claude Desktop Code CLI architecture, Gemini Workspace and AI Studio deployments, Grok Team Collaboration mode, and how providers adapt system prompts for different deployment contexts. Documents how system-level instructions vary between web interface, API, and specialized workspace deployments.

Documents how different AI providers implement conversation memory, user preference persistence, and context window management through system-level instructions. Captures Claude's past conversation and memory system with search/fetch capabilities, GPT-5.4's memory and bio systems with user update cadence, Gemini's workspace-level context persistence, and Grok's team collaboration memory architecture. Enables understanding of how models are instructed to retrieve, prioritize, and forget information across conversation turns.

Extracts and documents safety guardrails, content filtering policies, and alignment constraints embedded in system prompts across providers. Captures Claude's security architecture and prompt injection defense mechanisms, GPT-5.4's safety constraints and personality-based behavior modulation, Gemini's chain-of-thought protection and security policies, and Grok's policy layer architecture. Enables analysis of how providers encode safety rules, handle adversarial inputs, and balance capability with constraint.

Extracts and documents how AI providers implement personality systems, behavioral variation, and tone modulation through system prompts. Captures GPT-5's personality framework with Listener (warm, reflective), Nerdy (playful, scientific), and Cynic (sarcastic with hidden warmth) variants, Grok's persona and companion system, and how personality constraints affect artifact handling and response style. Enables understanding of how models are instructed to vary behavior based on user context or explicit personality selection.

Extracts and documents how AI providers implement artifact generation, code block handling, and structured output formatting through system prompts. Captures how Claude handles artifacts with Anthropic API integration, how GPT-5.4 manages artifact generation and skills integration, and how different providers constrain code output formatting. Documents system-level instructions for when to generate artifacts, how to structure them, and how to handle multi-file or complex code generation.

Extracts and documents how AI providers integrate with external services and APIs through system prompts. Captures Claude's integrations with Slack, Gmail, and Google Workspace, Gemini's search and browse tool architecture, Perplexity's browser and voice assistant integrations, and how providers handle API authentication, error handling, and capability constraints. Documents system-level instructions for API orchestration, rate limiting awareness, and multi-service coordination.

Maintains version-controlled documentation of system prompts across model generations and variants, enabling longitudinal analysis of how AI providers evolve their architectures. Tracks changes from GPT-4 through GPT-5.4, Claude Sonnet through Claude Opus 4.6, Gemini 2.5 through 3.1 Pro, and Grok 3 through 4.2. Documents how capabilities are added, deprecated, or modified across versions, and how system-level instructions change to support new features or address discovered issues.

Enables comparative analysis of architectural patterns across different AI providers by aggregating system prompts in a structured format. Supports identification of common patterns (tool integration, memory systems, safety constraints, personality frameworks) and provider-specific innovations. Facilitates analysis of how different providers solve similar problems (e.g., context window management, tool calling, artifact generation) using different architectural approaches.

Maintains both raw extracted system prompts and human-readable markdown variants with annotations, enabling different use cases for prompt analysis. Raw variants preserve exact formatting and structure as extracted from providers, while markdown variants add section headers, formatting, and explanatory notes for easier reading and analysis. Supports both programmatic analysis of raw prompts and human-readable study of architectural decisions.