AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
grounding — Tying a model's answers to checkable sources — retrieved documents, live data, tool results — instead of letting it answer from memory alone.
Why it matters
It gives you a shared vocabulary and decision framework for AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → architecture — which composable workflow pattern fits your problem, and when you don't need an agent at all — groundingTying a model's answers to checkable sources — retrieved documents, live data, tool results — instead of letting it answer from memory alone.Full definition → in first-party guidance from the lab that ships Claude's tool-use and agent APIs.
Key quotes
“Workflows are systems where LLMs and tools are orchestrated through predefined code paths.”
“Agents, on the other hand, are systems where LLMs dynamically direct their own processes and tool usage, maintaining control over how they accomplish tasks.”
“We suggest that developers start by using LLM APIs directly: many patterns can be implemented in a few lines of code.”
“While building our agent for SWE-bench, we actually spent more time optimizing our tools than the overall prompt.”
