# Kranth glossary

- **Archetype** — persona template (role / worldview). Kranth ships 101.
- **Bias axes** — sampling weights (e.g. finance, enterprise) that tilt the room.
- **Credit** — billing unit for a room (seats × model). A then B is included.
- **Compare (A then B)** — same people hit version A, then a rewrite B. The call is which to ship.
- **Debate** — multi-persona structured argument mode.
- **Hostile** — sentiment ≤ about −0.3; weighted more in scoring.
- **Persona** — single AI agent with traits and voice.
- **Recon** — web-grounded research mode.
- **Room** — informal name for a simulation or debate session.
- **Simulation (sim)** — same people hit A, then B. Call: ship B, keep A, or split.
- **Synthetic audience** — AI personas used as a stress-test panel, not real humans.
- **Verdict** — structured outcome: scores, the call, objections, themes, quotes.
- **Voice axes** — dimensions of speaking style (8 axes).
