Claude 101 · The mental model

An agent is something
you assemble.

Not a single feature — a composition. You start with a language model and attach the pieces it needs to solve one specific problem. Think of them as primitives you snap together.

agent = LLM + context + connections + capabilities + code  →  one domain problem
Base model
Claude
Watch the primitives attach to the model, one layer at a time.
+ 01

Context

what the model knows going in

Project

A persistent workspace bundling related chats, shared files, and instructions so context carries across conversations.

Memory

Details Claude retains about you and your work, so it doesn’t start from zero each time.

Instructions

The standing directions that shape how the agent behaves for its particular job.

+ 02

Connections

how it reaches your other software

Connector

A link into an outside service — Drive, Slack, a database — so the agent can read and act on real data. The user-facing on/off switch for one integration.

MCP

Model Context Protocol — the open standard connectors are built on, so one integration works across many AI apps. The plumbing under a connector.

+ 03

Capabilities

what it knows how to do

Skill

A packaged set of instructions and resources that teaches the model a specific job — build a slide deck, fill a PDF — loaded only when relevant.

Tools

Discrete actions the model can invoke: search the web, run code, read a file. The verbs available to the agent.

+ 04

Code

the deterministic glue

Code

The scripts and logic that wire everything together — orchestrating when the model thinks, when it calls a tool, and what happens with the result.

Artifact

What the assembled agent produces: a document, a chart, a working app. The output you keep. (This page is one.)

=

Where the agent runs

the runtime — how you actually put it to work
Surface 01

Claude

The chat app. You converse, it answers, makes artifacts, uses connectors. Where most people meet the agent.

Surface 02

Claude Cowork

A desktop runtime for knowledge work — research, sheets, slides, docs — where the agent runs tasks for you rather than just chatting.

Surface 03

Claude Code

The runtime for developers. The agent edits files, runs commands, and builds across a whole codebase from your terminal or editor.