Systems where AI agents execute multi-step tasks autonomously, raising interconnected questions about harness architecture, state management, reliability engineering, human oversight, and the organizational context those agents operate within.

LLM agents are software systems that pair a language model with tools, memory, and control flow to accomplish multi-step tasks autonomously; the emerging consensus is that reliability requires engineering constraints, not better prompts.

LLM orchestration covers the control structures, harness designs, and coordination patterns that govern how language models are invoked, sequenced, and supervised — whether in single-agent loops or across distributed multi-agent pipelines.

Multi-agent systems coordinate multiple LLM-backed agents to handle tasks too large or complex for a single context window, but empirical research shows failure rates of 41–87% in production, making coordination structure and verification as important as raw model capability.

RAG grounds LLM outputs in external knowledge at inference time; recent work questions when vector similarity retrieval is the right tool and what alternatives — hierarchical indexing, KV caching, compiled wikis — better serve different workloads.