Core concepts
An agent is data: a profile, what it is allowed to do, its tools, its skills, and
what fills its prompt. These six pages are the vocabulary everything else on this
site assumes. Each one has a runnable counterpart under
examples/.
- Agents — the profile, the three ways to create one, and every key on it.
- Limits and policy — the five layers that decide what an agent may do and what stops it.
- Tools — code tools, data-defined tools, MCP servers, and why a tool call goes missing.
- Skills — playbooks the agent loads only when the conversation calls for them.
- Context — what fills a turn’s prompt, the token budget, and cross-session memory.
- Workflows — when the order of work belongs in Ruby instead of a prompt.