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.

Table of contents


Back to top

Insika is MIT-licensed. Reading this as an agent? llms.txt indexes these docs as raw markdown.

This site uses Just the Docs, a documentation theme for Jekyll.