Sloth-Butler: Replies to the client messages you dread

Описание и применение

Sloth‑Butler – веб‑приложение, использующее fine‑tuned модель Qwen3‑8B LoRA для генерации вежливых, но решительных ответов клиентам, соблюдая заданные условия, с автоматическим планированием напоминаний и голосовыми заметками.

Задача

Freelancers and service sellers struggle to craft polite yet firm replies to client requests for free work, discounts, late invoices, or other unfavorable terms, leading to delayed responses and potential revenue loss.

Результат

The fine‑tuned model increased the percentage of replies that pass all five evaluation criteria from 41% to 63%, improved sendable rate from 84% to 93%, and reduced average reply length from 51 to 34 words.

Рабочий процесс

• Open https://sloth-butler.vercel.app
• Press "Write a reply"
• Fill and save "Your terms" once
• Select situation and paste client message
• Add amount/deadline, tone, language
• Press "Write my reply"
• Copy, play or download mp3
• For late invoices, press "Plan follow‑ups" and use board
• After sending, log hours and money protected

Доказательства

Base Qwen3-8B and the fine‑tune answered the same 100 held‑out messages with the same prompt, temperature 0.7 and seed 2026. A judge model (gpt-oss-120b) scored each reply 1 to 5 per criterion; a pass is 4 or more.

Источник

The model can still get numbers wrong. For example, it sometimes offers a discount when the job is already at your minimum price. The server‑side guard catches that and corrects the reply, but it's a code check, not the model getting it right.

Источник

Six languages: English, Spanish, French, Portuguese, German and Nigerian Pidgin.

Источник

Select a tone (soft, firm, maybe‑later) and a language.

Источник

The training loop is adapted from tinker‑cookbook's supervised recipe.

Источник