TheirSide resource desk
Evaluation records and field tools
Use the three evaluation v0.1 records—two fixed demos and one dated production guest test—to inspect narrow first-party observations, or open the template to shape a fictional character without an account. Evidence records and the editable workbook remain separate resource types.
Resource index reviewed
Evaluation v0.1 records
Two fixed demos and one controlled 10-run production record from the shared evaluation, with methods, failure criteria, observed results, and explicit limits.
- 01
AI character continuity inside one visible conversation
A fixed bilingual 1v1 demo shows how a fictional character keeps the user's scene framing and desired tone coherent across the same visible exchange, with strict limits on what that example proves.
- 02
Can one AI character respond to another? A 10-run production test
A dated production test ran one fixed English prompt in 10 fresh signed-out guest rooms with Mio and Kai. All 10 flows completed with Mio followed by Kai, and all 10 later Kai replies explicitly named Mio and continued from a run-specific idea before adding a complication.
- 03
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.
Templates
Practical browser-local tools you can use without sending draft content to TheirSide.
- 01
AI character profile template: a no-login field workbook
Shape a fictional character across nine practical fields, edit a complete example in browser memory, then copy versioned Markdown or download Unicode-safe JSON without creating an account.