中文

Attune — how to use it

A fidelity check on a message before you send it, and a decoder for the ones you get. Two minutes to learn.

Checking a message

  1. To — a name is enough ("Sam"). Already know something useful? Write it after the name: "Sam, my US manager, dislikes hedging". Either way the tool builds its picture of each person as you use it.
  2. What you want to say — your own words or a rough draft, any language. English is fine even if the message will go out in Chinese; the tool renders in the recipient's language.
  3. Their message — if you're replying, paste what you're answering. You'll get a reading of their message first (tone, what they likely mean — "terse, not angry"), then candidate replies that actually answer it. Or hit Read it for me for the reading alone, no reply. Starting fresh? Leave it empty.
  4. Hit Attune. You get: what the tool understood you to mean (check this first), two candidate messages, and — for each — how it's likely to land on a cold read.
  5. Copy the one that matches your intent and send it yourself. The tool never sends.
A candidate message with its predicted reception: tone as heard, likely reaction, misread risks, questions left open
One candidate and its cold read: how it's likely taken, the tone heard, what could be misread, what it leaves unanswered.
A terse reply decoded: direct and decisive, not anger, with alternative readings and a clarifying question
"fine. send it monday." — read for you: terse is not angry, with the other plausible readings ranked and a question that beats guessing.

Channels — why it gets better

Everyone you write to becomes a channel, automatically. The tool builds a private model of each one: which register you tend to choose, what has misfired before, how they read tone. The third message to someone knows things the first couldn't. Reports of how a message actually landed teach it fastest — and those arrive on their own: when their reply comes back through the tool, it checks the reply against what it predicted and records whether the message landed. "Erase" at the bottom of the page removes everything.

A channel card: 3 runs, 3 of 3 landed, each with predicted tone versus the auto-settled outcome
A channel after three messages: every prediction checked against the actual reply, on its own.

Limits

Tips

← back to the tool

Attune — 使用說明

訊息寄出前,先檢查它會被怎麼讀;收到的訊息,也替你解讀。兩分鐘上手。

檢查一則訊息

  1. 寫給——名字就夠了(「小明」)。已經知道一些有用的背景?接在名字後面寫: 「小明,我的美國主管,不喜歡拐彎抹角」。無論寫多寫少,工具都會隨著你的使用, 慢慢累積對每個人的了解。
  2. 你想說什麼——自己的話或粗略草稿都行,任何語言皆可。就算訊息最後要用中文寄出, 用英文輸入也沒問題;工具會以收件人的語言寫出訊息。
  3. 對方的訊息——如果你是在回信,把對方的訊息貼上來。工具會先解讀對方 的訊息(語氣、大概想說什麼——「簡短,不是生氣」),再給出真正回應到問題的候選回覆。 也可以按幫我讀這封,只看解讀、不寫回覆。全新的訊息?留空即可。
  4. 按下 Attune。你會得到:工具理解到的你的意思(先確認這個)、兩則候選訊息, 以及每一則在不帶背景的冷讀下,可能怎麼落地。
  5. 複製符合你本意的那一則,自己寄出。工具永遠不會替你寄送。
一則候選訊息與它的預測接收:聽到的語氣、可能的反應、誤讀風險、沒回答到的問題
一則候選訊息與它的冷讀:可能被怎麼理解、聽到的語氣、 哪裡可能被誤讀、還有什麼沒回答到。
一封簡短回覆的解讀:直接、果斷,不是生氣,附上其他可能的讀法與一個釐清問題
「fine. send it monday.」——替你解讀:簡短不等於生氣, 並列出其他說得通的讀法,附上一個勝過瞎猜的問題。

管道——為什麼越用越準

你寫信的每一個對象,都會自動成為一個管道。工具替每個管道建立一份私有的模型: 你偏好選哪種語氣層次、以前哪裡失手過、對方怎麼讀語氣。寫給同一個人的第三封訊息, 知道第一封不可能知道的事。最能教會它的,是訊息實際落地的結果——而這些會自己送上門: 當對方的回覆再次經過工具,它會拿回覆對照當初的預測,記下這封是否如預期。 頁尾的「清除」會刪掉全部紀錄。

一張管道卡片:3 次,3/3 如預期,每次都有預測語氣與自動核對的結果
三封訊息之後的管道:每個預測都自動對照過實際回覆。

限制

訣竅

← 回到工具