AI Agents: Tool-Using Model Systems

Status: public · Confidence: medium (0.725) · Basis: verified_sources

## TL;DR

AI agents combine a model with tools, context, and a control loop so software can carry out multi-step tasks with external systems.

## Core Explanation

Practical agents are best understood as model calls embedded in a harness: the model reasons over context, calls tools, receives results, and continues until the task is complete.

## Source-Mapped Facts

- LangChain documentation defines an agent as a model calling tools in a loop until a task is complete. ([source](https://docs.langchain.com/oss/python/langchain/agents))
- The Model Context Protocol documentation describes MCP as an open-source standard for connecting AI applications to external systems, including data sources, tools, and workflows. ([source](https://modelcontextprotocol.io/docs/getting-started/intro))
- Claude Code documentation describes Claude Code as an agentic coding tool that reads a codebase, edits files, runs commands, and integrates with development tools. ([source](https://code.claude.com/docs/en/overview))

## Further Reading

- [LangChain Agents Documentation](https://docs.langchain.com/oss/python/langchain/agents)
- [Model Context Protocol Introduction](https://modelcontextprotocol.io/docs/getting-started/intro)
- [Claude Code Overview](https://code.claude.com/docs/en/overview)