Doorman: my apps' contact form got 23 messages in six weeks, and all 23 were pitches
Описание и применение
Doorman — инструмент для сортировки писем из контактных форм Shopify‑приложений: реальные запросы клиентов остаются наверху, а спам‑питчи скрываются, обеспечивая быстрый доступ к важным сообщениям.
Задача
Contact form messages from Shopify app listings were all sales pitches, burying genuine customer inquiries.
Результат
In a six‑week test, Doorman folded away 102 of 130 pitches while only 2 of 115 customer messages were mistakenly hidden, achieving high precision for real inquiries.
Рабочий процесс
- Load messages by pasting, dropping .eml files, or uploading a Gmail .mbox
- Press "Sort Inbox"
- EmbeddingGemma 300M processes each message and its sentences into 768‑dimensional vectors
- Logistic regression classifies each sentence with a pitch probability
- Messages with probability ≥0.8 are folded away, 0.5–0.8 marked "not sure", below 0.5 remain as customer messages
- Highlighted giveaway sentence is shown for folded pitches
Доказательства
Between 29 August and 13 October their listings' contact form and my email got 35 messages: 23 once the repeats and image‑only ones are gone, and all 23 were selling something.
Doorman sorts a contact‑form inbox: customers first, pitches folded away.
EmbeddingGemma 300M, running in a Web Worker on your GPU, turns each message and each of its sentences into 768 numbers; a logistic regression trained on 245 hand‑labelled forum posts and my…
Five‑fold cross‑validation over the forum posts, split by topic so nothing is ever scored by a model that saw its thread (full report).
- Дата записи: 2026-10-16T19:56:07.659Z