# Concepts

Core vocabulary: what a box, a card, and the engine are.

- [cards.md](https://beebox.run/docs/concepts/cards.md): The card format: YAML frontmatter plus a markdown body.
- [chat-schedules.md](https://beebox.run/docs/concepts/chat-schedules.md): Timers the agent sets from chat that fire later.
- [connectors.md](https://beebox.run/docs/concepts/connectors.md): What a connector is: the sync boundary between an external service and the box filesystem.
- [enriched-markdown.md](https://beebox.run/docs/concepts/enriched-markdown.md): Cards are markdown enriched in specific ways: a header that each kind of card extends, and a body with a small baseline of cross-cutting marks (quote, source, todo) that any card can use.
- [glossary.md](https://beebox.run/docs/concepts/glossary.md): Bee Box terms, one line each.
- [landmarks.md](https://beebox.run/docs/concepts/landmarks.md): Landmarks: the short curated navigation surface over a box.
- [model-policy.md](https://beebox.run/docs/concepts/model-policy.md): Which engine (Claude Code or Codex) and which model tier a box thinks with.
- [procedures.md](https://beebox.run/docs/concepts/procedures.md): Procedures: multi-step workflows expressed as cards and run by the engine.
- [questions.md](https://beebox.run/docs/concepts/questions.md): The questions subsystem: how the agent asks, where answers go, and what they change.
- [triage.md](https://beebox.run/docs/concepts/triage.md): The intake pipeline: how an inbox item is classified, filed, or turned into a question.