10xGraphv0.9.2Search

    Glossary

    In this sectionPlain definitions of AI agent terms, from ReAct agents and state graphs to MCP, RAG, durable execution and idempotent tool calls, with Python examples.

    • 10 pages
    • About 33 min to read all

    The glossary defines the terms that come up most often when building Python AI agents, from basic patterns such as the ReAct loop to the production concerns that decide whether an agent survives real traffic. Each entry opens with a short definition, then explains how the concept is used in practice, with Python examples written for 10xGraph. It is for engineers who meet a term in a design discussion or a paper and want a precise answer before reading further.

    Start here

    New to agents? Read What is an AI agent?, then What is a ReAct agent? for the tool-calling loop most agents are built on, and What is a state graph? for how 10xGraph models a workflow as nodes and edges.

    If you are heading to production, two terms matter most. What is durable execution? explains how a run can survive a crash and resume, and What is an idempotent tool call? explains how to avoid charging a card or sending an email twice when that resume happens. Both connect to Replay-safe tools, the 10xGraph mechanism that records finished tool calls so they are not re-executed.

    For connecting an agent to the outside world, read What is the Model Context Protocol?, and for state across turns, What is agent memory?.

    Core concepts

    Term Definition
    What is an AI agent? A program that uses an LLM to perceive inputs, reason, call tools, and take actions in a loop to complete multi-step tasks
    What is a ReAct agent? An agent that alternates between Reasoning and Acting steps - calling tools, observing results, and reasoning again until it has an answer
    What is multi-agent orchestration? Coordinating multiple specialized AI agents so they collaborate on a shared goal, with explicit handoffs and control flow
    What is a state graph? A graph-based model for agent workflows where nodes are processing steps and edges define how state moves between them
    What is agent memory? The mechanisms by which an AI agent stores and retrieves information across turns, sessions, and restarts
    What is the Model Context Protocol (MCP)? An open standard that lets AI agents connect to external tools and data sources through a common interface
    What is RAG? Retrieval-Augmented Generation - a pattern where an agent retrieves relevant documents before generating a response
    What is durable execution? Running a workflow so progress is saved and a crashed run resumes where it stopped instead of starting over
    What is an idempotent tool call? A tool call that can run more than once without repeating its side effect, such as a second charge or email
    What is agent streaming? Sending AI agent responses token-by-token to a frontend instead of waiting for the full response to complete

    All pages in Glossary

    1. What Is an AI Agent? Definition and Python Guide (2026)An AI agent is a program that uses an LLM to perceive input, reason, and act in a loop until a goal is met. Learn the patterns and build one in Python.3 min
    2. What Is a ReAct Agent? Python Guide with Code ExamplesA ReAct agent alternates reasoning and acting: it calls tools, observes the results, and reasons again. Learn how it works and build one in Python.3 min
    3. What Is Multi-Agent Orchestration? Python GuideMulti-agent orchestration coordinates several AI agents toward one goal using explicit handoffs and control flow. See the patterns with Python examples.3 min
    4. What Is a State Graph? AI Agent Architecture GuideA state graph models AI agent workflows as nodes (processing steps) and edges that move state between them. See how it works with Python examples.3 min
    5. What Is Agent Memory? Types and Python ImplementationAgent memory is how an AI agent stores and retrieves information across turns, sessions, and restarts. See the three memory types and Python code.3 min
    6. What Is the Model Context Protocol (MCP)? Guide for AI AgentsThe Model Context Protocol (MCP) is an open standard that connects AI agents to external tools and data through one interface. Learn how to use it in Python.4 min
    7. What Is RAG (Retrieval-Augmented Generation)? Python GuideRAG (Retrieval-Augmented Generation) has an agent retrieve relevant documents before it answers. Learn how it works and build a RAG agent in Python.3 min
    8. What Is AI Agent Streaming? SSE Guide for PythonAI agent streaming sends responses token-by-token to a frontend over SSE instead of waiting for the full reply. Learn how it works in Python.4 min
    9. What Is Durable Execution for AI Agents?Durable execution saves a run's progress so it resumes after a crash instead of restarting. See what it covers for AI agents and how 10xGraph implements it.4 min
    10. What Is an Idempotent Tool Call?An idempotent tool call has the same effect whether it runs once or many times. See why agents need it, how idempotency keys work and how 10xGraph helps.3 min