AI Agent Vocabulary
Core terms for autonomous agents, agentic workflows, and agent infrastructure.
▸ 15 TERMSAgent Loop
An agent's think → call tool → observe → repeat loop until the goal is met. Most modern AI apps are this loop.
Agent Memory
System for an agent to store and recall information within or across sessions. Short, long, episodic, semantic flavors.
Agent Graph
LangGraph's state-machine model where nodes = agents/tools and edges = handoffs. Makes complex flows visualizable.
Agent Swarm
A loosely coupled, parallel-running group of many small agents. Ant-colony logic; OpenAI Swarm exemplifies this idea.
Agent Router
Front-layer that routes incoming prompts to the most fitting specialist agent. Optimizes cost and quality.
Agent Trace
Full log of an agent run including every LLM call, tool, observation. LangSmith, Braintrust, Helicone surface it.
Agentic Workflow
A workflow chaining planning + tools + verification steps instead of a single LLM call.
Agentic Search
Agent doing query → search → evaluate → new query in a loop instead of one search. The basis of modern web research.
Tool Use
When the model decides to invoke a function instead of generating text. Same as "function calling." The core of agentic behavior.
Chain of Thought
Pushing a model to reason step-by-step to solve harder problems. Often as simple as "think step by step."
Autonomous Mode
Mode where the agent takes all actions without human approval. "Full auto", "--dangerously-bypass". Trust mandatory.
Approval Mode
Mode where every risky action prompts the user for approval. Claude Code default; the opposite of YOLO.
Browser Use
Agent driving a browser to navigate, fill forms, and scrape. Built on libraries like browser-use or Playwright MCP.
Coding Agent
Agent specialized for software work: Claude Code, Cursor Composer, Aider, Devin, Codex, OpenHands.
Anthropic Agent SDK
Anthropic's TypeScript/Python agent library. First-class tool use + computer use + streaming.