← Kioko · lens 3 / 5Training · how she adapts
Adaptation · behavior · steering

Shape her.
Watch her change.

Loading...
How she adapted over time
01Chapter 01 / 05Adaptation timeline

What she
learned.

After every conversation, Kioko reflects — what did she pick up, what did she ignore, and how should future replies change. This is the raw log of her learning.

No reflections yet — talk to Kioko and she'll start learning
Current per-mode steering
02Chapter 02 / 05Behavior profile

How she
behaves now.

Five steering dimensions per mode — loaded directly from the backend. These are the values actually applied to the system prompt at generation time.

loading live steering…
Direct behavior shaping
03Chapter 03 / 05Steering controls

Take the
wheel.

Adjust any mode directly. Changes persist to the backend and apply to the next generation. Try the Switchboard afterward to compare outputs.

loading mode configs…
Live preview· HONNE 本音
idle
test prompt

Move a slider above or hit run — this reply regenerates as her steering changes. No memory, pure voice.

Every steering change auto-reruns after 600ms. Pause to edit without burning requests.

Per-mode tone & pattern memory
04Chapter 04 / 05Mode tuning

Three voices,
diverging.

Each mode develops its own tone and pattern memory through conversation. HONNE learns warmth cues, YAMI learns what provokes honesty, SHIN learns what structure works.

HONNE
No tone or pattern memories yet
YAMI
No tone or pattern memories yet
SHIN
No tone or pattern memories yet
The reasoning behind her words
05Chapter 05 / 05Why she changed

The reasoning
behind her words.

Every response is traced — which memories were retrieved, what model ran, what adaptation rule came out of the reflection. Expand any entry for the full picture.

loading traces…

Talk to her. Every message teaches.

offline
waiting for her first turn…