Patterns

Recurring architectural and design patterns in AI/LLM systems — RAG, tool calling, routing, guardrails, and more.

Contents

Common Patterns

• RAG (Retrieval-Augmented Generation) — Grounding LLM output with retrieved context
• Tool Calling / Function Calling — LLMs invoking external tools via structured schemas
• Routing — Directing queries to specialised models or agents
• Guardrails — Input/output validation and safety filtering
• Chain-of-Thought — Structured reasoning prompts
• Multi-Agent Collaboration — Multiple agents coordinating on a task