We Paid to Reprint 2,000 Report Cards. So We Gave Our Support Team a Memory.
Описание и применение
Система Ednovax Support использует FalkorDB для хранения и поиска информации из WhatsApp, обеспечивая отслеживание запросов, обещаний и связей с кодом, что предотвратило дорогостоящий повторный печатный выпуск 2000 справок.
Задача
Support requests from schools were lost in WhatsApp chats, leading to missed promises and a costly reprint of 2,000 report cards.
Результат
The system reduced missed promises, avoided costly reprints, and provided a structured memory of support interactions, code dependencies, and owner assignments.
Рабочий процесс
- 1. Receive WhatsApp message
- 2. AI triage classifies message as bug, question, etc.
- 3. FalkorDB retrieves related tickets via vector search
- 4. Reuse existing ticket or create new one
- 5. Link ticket to message, school, feature, and code files
- 6. Assign developer owner and create GitHub issue
- 7. Track promises and send reminders
- 8. Close loop when PR merges and teacher confirms
Доказательства
We found out after the printing was done.
We lost track. Which school asked for what, and when? It was scattered across personal chats and group threads.
We built on FalkorDB. It gave us four things we needed in one place: Cypher queries, vector indexes, graph algorithms, many graphs in one database.
The desk links the message to a ticket. The four teachers in the live demo are played by AI.
- Дата записи: 2026-10-17T22:41:31.130Z