Real World Systems
How the most widely-used AI systems are actually built. Each breakdown maps the system's architecture to the patterns in this catalog — showing which patterns they use, how they combine them, and where they diverge.
These are not speculative designs. Every detail is sourced from official documentation, open source code, published research, reverse engineering, and system cards.
The systems
| System | Builder | Type | Core Pattern |
|---|---|---|---|
| Claude Code | Anthropic | Coding agent (CLI) | ReAct loop + sub-agents |
| ChatGPT | OpenAI | Conversational AI | Router + tool orchestration |
| Cursor | Cursor Inc. | AI code editor | Multi-model routing + RAG |
| Devin | Cognition Labs | Autonomous coding agent | Plan-and-execute + full VM |
| GitHub Copilot | GitHub / Microsoft | Coding assistant | FIM completion + RAG |
| Perplexity | Perplexity AI | Answer engine | RAG pipeline + citation |
| OpenClaw | Peter Steinberger | Autonomous agent platform | Channel adapters + sandboxed tools |
Patterns in the wild
Every system in this section combines multiple patterns from the catalog. Common combinations:
Coding agents (Claude Code, Devin, Cursor Agent) tend to use ReAct or Plan-and-Execute for reasoning, a Tool Router for function calling, and File-Based Memory for persistence.
Conversational systems (ChatGPT) lean on Router patterns for tool selection, layered Guardrails for safety, and multi-tier memory systems.
Search-augmented systems (Perplexity) are built around RAG with Citation and multi-stage ranking pipelines.
IDE-integrated tools (Cursor, Copilot) combine RAG for codebase context with speculative decoding and model routing for latency optimization.
Messaging-first agents (OpenClaw) use a Router pattern for channel normalization, File-Based Memory with hybrid semantic search, and session-based trust boundaries with Human-in-the-Loop pairing.