AI Agents and the AI Harness
AI agents are artificial systems that perceive their environment, reason about goals, use tools, and take actions to complete tasks with limited human supervision. They are distinguished from conventional AI models by autonomy, persistent state, and the capacity to act: rather than answering a single prompt, an agent runs a loop of reasoning, action, and observation that continues until a goal is met or a stop condition ends the run. Agents range from simple reflex mechanisms governed by condition–action rules to language-model-driven systems that plan, maintain memory, delegate to sub-agents, and operate over long horizons.
The central insight of contemporary agent engineering is that the model alone does not determine an agent's value. The surrounding software layer — the harness — supplies context assembly, tool execution, memory, permissions, verification, and the control loop that connects the model to its environment. This relationship is commonly summarized as Agent = Model + Harness: the model provides reasoning, while the harness provides action, state, and limits. Production failures in agent systems are frequently engineering failures rather than model failures, and controlled changes to scaffolding can produce larger capability gains than model upgrades on the same underlying model.
This wiki covers the domain end to end. It treats the foundational concepts — the agentic loop, tool use and function calling, autonomy levels, context and memory — and the architecture of agent systems, including planning and reasoning, multi-agent coordination, retrieval-augmented generation, and memory systems. It examines the harness as a discipline in its own right: its layered architecture, orchestration and control flow, sandboxing and permissions, observability, human-in-the-loop mechanisms, and error recovery. It surveys what agents can do today, from coding and computer use to research, customer service, and enterprise automation; the models, frameworks, and protocols used to build them; the risks of hallucination, prompt injection, misalignment, and over-privilege; how agents are evaluated, tested, governed, and regulated; and their economic and labour consequences. It closes with the history of the field and its outlook.