Skip to content
ReviewRamble

The weekly brief

AI, reviewed, in your inbox.

  • New reviews of tools, models, MCP servers and repos, with the verdict up front
  • Re-checked prices and ratings when something changes
  • New analysis pieces as they are published

Models, agents, MCP servers and the tools actually worth your time.

One email a week. Unsubscribe with the link in any brief. How we use your email

AI agent

An AI agent is a system in which a language model decides its own next steps: it calls tools, reads the results and repeats until the task is done, instead of following a fixed script.

Also called: agent, autonomous agent

By Divya Sharma · Checked Nov 15, 2026 · How we review

A chatbot answers one message at a time. An agent is given a goal and works toward it over many steps, choosing which tools to call along the way. A tool might search the web, query a database, edit a file or run a test.

How it works

At its core an agent is an agent loop. The model reads the task and the results so far, then either asks for a tool through tool calling or gives a final answer. The application runs each tool and feeds the output back. Tools often come from servers that speak the Model Context Protocol.

Anthropic draws a line between agents and workflows. In a workflow, the developer's code fixes the order of steps. In an agent, the model directs its own process and decides which tools to use.

Example

Asked to fix a failing test, a coding agent such as Claude Code reads the error, opens the relevant files, edits one, reruns the test and stops when it passes.

Limits

More autonomy means more ways to go wrong. Agents cost more and take longer than a single model call, errors can compound across steps, and an agent with broad tool access can do real damage. Start with the simplest setup that works, test in a sandbox and keep a person able to approve risky actions. The agent frameworks guide compares the main toolkits.

Related terms

Agentic AI
Agentic AI describes software in which a language model has some control over how a task gets done: it plans steps, picks tools and acts on the results, with more autonomy than a single prompt and reply.
Agent loop
An agent loop is the repeating cycle at the heart of an AI agent: the model asks for a tool call, the application runs it and returns the result, and the model decides what to do next.
Tool calling
Tool calling, also called function calling, is a model API feature where you describe functions with a schema, the model replies with a structured request to call one, and your code runs it and returns the result.
Model Context Protocol
The Model Context Protocol (MCP) is an open standard that defines how AI applications connect to external tools, data and prompts, using JSON-RPC messages between a host application, its clients and separate servers.
Multi-agent system
A multi-agent system is a setup in which several AI agents, each with its own instructions, tools and context, work on parts of a task and pass results to each other or to a coordinating agent.

Sources