Evidence recordscripted-ai-story-scenes

Fixed demo evidence

TheirSide Character Continuity and Multi-Character Turn-Taking Evaluation

v0.1

What a scripted AI story scene establishes at the opening

A fixed bilingual story-page demo documents the visible opening state of a scripted scene—status, role context, known facts, and two character lines—without predicting later branches or endings.

Direct answer

TheirSide's fixed story demo shows a scripted scene already in an opening state before the user's next message: the scene is marked live, role and known-fact context is visible, and Mio and Kai each have an authored line. This supports a claim about scene setup only; it does not establish how later branches, outcomes, or endings will unfold.

English fixed TheirSide story scene opening with visible status and two labeled character lines
Fixed authored demo from the public English ai-story-group-chat page; it contains no customer data.

Where this applies

  • Reviewing what context is visible before a user writes the next line of a story scene.
  • Checking whether multiple character names and opening positions are present in one scene frame.
  • Distinguishing a scripted opening state from claims about complete narrative generation.
01

Method

We reviewed the fixed public ai-story-group-chat image, inventoried the visible scene-state labels and character lines before the empty reply field, and avoided treating the authored opening frame as evidence about any later interactive path.

02

Scenario provenance

The opening is a fixed synthetic story frame authored by the TheirSide team for the public ai-story-group-chat page. Its live-state label, role context, known facts, and Mio and Kai lines were arranged to make the pre-reply setup inspectable without using a customer conversation.

03

Failure criterion

Mark the opening-state check as failed if the frame omits the visible scene status, lacks role or known-fact context, or fails to distinguish the two authored character lines before the user's next reply. Later branches and endings are not scored by this record.

04

Test steps

  1. 01

    Locate the scene state

    Confirm that the interface marks the story scene as live before a new user reply is entered.

  2. 02

    Inventory opening context

    Record the visible references to role slots, known facts, and the user's next reply.

  3. 03

    Identify character lines

    Confirm that the opening frame includes separately labeled lines from Mio and Kai.

  4. 04

    Stop at the opening boundary

    Do not infer later choices, branches, outcomes, or an ending from the fixed pre-reply state.

05

Observed result

The screenshot visibly marks the story scene as live, names role slots and known facts, leaves the next-reply field open, and displays one authored line each for Mio and Kai. It therefore documents a prepared opening state for a multi-character story scene.

06

Limits of this evidence

This fixed authored opening does not test later branches, outcomes, or endings. It does not measure narrative quality, continuity after the next reply, or whether every account has identical scene availability, and it is not evidence of an autonomous story completing without user input.

07

Sources and ownership

Version
1.0
Published
Reviewed
Maintained and reviewed by
TheirSide
What a scripted AI story scene establishes at the opening | TheirSide