I Built an AI That Remembers the Promises We Forget

Описание и применение

Приложение PromiseKeeper использует локальную модель Qwen для извлечения и управления обещаниями из заметок и чатов, позволяя исследователям быстро находить и подтверждать договоренности.

Задача

Researchers often forget informal agreements made in meetings or chats, making it hard to track commitments and deadlines.

Результат

PromiseKeeper successfully extracts three actionable promises from five synthetic note snippets, surfaces them with source quotes, and allows a reviewer to approve one overdue report and draft follow‑ups.

Рабочий процесс

• Import notes or text
• Local Ollama/Qwen extracts candidate promises
• Model proposes fields (action, owner, recipient, deadline, condition, certainty, evidence quote, next step)
• Pydantic validates schema
• API verifies evidence quote is a literal substring of source
• Human reviewer approves, edits, or dismisses each promise
• Approved promise becomes a draft follow‑up
• User reviews and sends draft (no sending integration)

Доказательства

Import meeting notes, a chat transcript, or a text file. A local language model proposes commitments.

Источник

The reviewer can approve it, correct it, dismiss it, or mark it complete.

Источник

The app is built around the difference between a possible promise and a confirmed one.

Источник

The recording follows a researcher importing five snippets of synthetic notes. Actual local Qwen inference finds three candidates: a revised field report, cleaned survey figures, and a conditional appendix.

Источник