Why the AI character would not calm down, and how I fixed it

Описание и применение

Персонаж ИИ в Say It Ahead не успокаивался, несмотря на попытки пользователя, что делало практику бессмысленной. Внедрение модели из четырёх задач (признание, уточнение, отражение, переход к действию) и инструмента обновления прогресса позволило персонажу постепенно смягчаться и давать пользователю визуальный отклик.

Задача

The AI character in Say It Ahead remained upset despite user attempts to calm it, making practice feel arbitrary and ineffective.

Результат

The character now adapts its tone based on user actions, providing a clearer sense of progress and reducing arbitrary outcomes.

Рабочий процесс

• Define scenario with character mood, beliefs, facts, and desired resolution.
• Structure the conversation around four jobs: acknowledge, clarify, reflect, move forward.
• During the call, the AI calls update_practice_progress to report the highest job completed and evidence from user input.
• The UI displays progress silently, giving users visual feedback without breaking role‑play.
• After the call, ElevenLabs runs a separate review to score each job and maps results to the review screen.
• Compare live progress with post‑call review to identify discrepancies and refine criteria.
• Iterate tests with varied wording to reduce variation and improve consistency.
• Deploy updated model in production.

Доказательства

The live character can use a browser tool called update_practice_progress. It sends the highest job completed and a short piece of evidence from what the user actually said.

Источник

The current guided scenarios use four broad jobs: acknowledge the concern, ask a useful question, reflect what you heard, and agree on a specific next step.

Источник