What this covers
The pain: you draft a Slack message, reread it, and it lands as either too soft (“just wanted to circle back if possible…”) or too sharp (“this is blocking me, please respond”). Either version costs you a reply or a relationship. This workflow uses AI as a tone rewriter for Slack drafts — input your raw thought, get back a version that is direct, kind, and ends with the specific action you want. The trick is feeding AI the relationship context, not just the words, so it does not produce generic corporate phrasing.
Who this is for
Anyone whose work happens in Slack threads — engineers asking for code review, PMs nudging a designer, managers giving feedback, founders chasing investor intros, and ICs who freeze before sending a hard message. Especially useful for non-native English speakers who want tone confidence without sounding like a chatbot, and for direct-by-default people whose messages keep landing harder than they meant.
When to reach for it
Before sending any message where the wrong tone has a real cost — chasing a slipped deadline, pushing back on scope, asking for help, raising a concern with a peer, declining a request. Skip it for routine acknowledgments, emoji replies, and threads where you already know the relationship is high-trust enough that tone does not matter.
Before you start
- Have your raw draft in front of you, even if it is one ugly sentence. AI rewrites are better with a starting point than with a brief.
- Know the relationship in one line: “peer engineer, high trust, has missed the last two reviews” gives AI 80% of what it needs.
- Decide the outcome you want from the message in one sentence. Not the message — the outcome. “I want a code review by Thursday” not “I want to mention the PR is open”.
- Pick a single chat surface for the rewrite step. Switching between ChatGPT, Claude, and Slack AI dulls your prompt muscle.
- Have one sample of your real voice saved somewhere. Paste it in so AI rewrites in your tone, not a generic corporate tone.
Step by step
- Write the ugly draft. Two sentences max — what is going on, what you want. Do not polish it.
- Paste it into AI with this scaffold:
Rewrite this Slack message. Relationship: [one line]. Desired outcome: [one line]. Tone target: direct, kind, no corporate softeners ("just wanted to", "circling back", "hope this finds you well"). End with the specific ask and a deadline. - Read the rewrite aloud. If it sounds like a person you would respect saying it to you, it passed. If it sounds like a press release or a HR memo, ask for “drop one level of formality”.
- Check the ask is single, specific, and time-bound. Multi-asks dilute the thread; vague asks get ignored.
- Edit one word. Even one word of your own voice transforms an AI-rewritten message from “polished” to “real”. The receiver senses the difference even when they cannot name it.
- Send. If you hesitated more than 30 seconds reading the rewrite, the draft was right and the rewrite is fine — your hesitation is the cost of doing the message at all.
First-run exercise
Pick three messages you sent in the last week that did not get the response you wanted. For each, write the original outcome in one line, run the rewrite workflow, and compare. You will find one of three things: the tone was actually wrong (good — workflow paid off), the ask was vague (better — fix it next time), or the message was fine and the receiver was the problem (also good — stop blaming your tone). The first run is a free calibration of which of your drafts actually needed rewriting.
Quality check
- The message ends with one specific ask and a deadline. Two asks split the receiver’s attention; no deadline gets deprioritized.
- Read aloud, it sounds like you, not like a customer-service script. Customer-service voice (“Thank you for your patience, I appreciate your time…”) signals you do not actually care about the outcome.
- No softener words you would not say in person: “just wanted to”, “I hate to ask”, “if it is not too much trouble”. They invite the receiver to say no by default.
- Length is under 4 sentences. Slack messages over 4 sentences turn into threads where everyone reads the first line and misses the ask.
- The first sentence has the most important information. People scroll past second sentences in Slack.
How to reuse this workflow
- Save 3 rewrite prompts as snippets: one for “chasing a slipped deadline”, one for “pushing back on scope”, one for “asking for help”. Most Slack tone problems map to one of these three.
- Keep a
voice/doc with 5-10 samples of messages you wrote that landed perfectly. Paste it as context every time. AI rewrites get sharper every month. - Track which rewrites get the outcome you wanted. After a month, you will see which scaffolds actually work for your team.
- Build a “phrases I avoid” list — corporate softeners and passive-aggressive tells — and feed it as constraints to the rewriter.
- For recurring threads (1:1 followups, sprint nudges), save the rewritten template and tweak per instance instead of regenerating.
Recommended workflow
Ugly draft in 2 sentences → AI rewrite with relationship line, desired outcome, tone constraints → read aloud → edit one word of your voice in → send. For high-stakes messages (raising a concern with a manager, declining a request from a senior peer), run two rewrites and pick the one that is harder for you to send — that is usually the more honest one.
Common mistakes
- Asking AI to “make this nicer”. You get corporate softeners and lose the direct ask. Ask for “direct and kind” instead.
- Skipping the relationship line. Without it, AI defaults to formal-strangers tone, which reads cold to a peer.
- Sending the rewrite verbatim. The receiver senses generic phrasing even when they cannot name it. One word of your own voice fixes this.
- Letting the rewrite balloon to 6 sentences. Slack rewards 2-3 sentence messages; AI defaults to longer.
- Two asks in one message. The second ask gets dropped, then resentment when nothing happens.
- Rewriting messages that did not need rewriting. The workflow has a cost; not every Slack message is high-stakes.
FAQ
- Will the receiver notice the message is AI-rewritten?: Not if you edit one word of your own voice in. The “AI sound” is generic phrasing, which you remove by being specific.
- What about messages in another language?: Tell AI the target language and ask for natural register. Non-native rewrites often over-formalize; constrain with “casual Slack register”.
- Should I rewrite emoji replies?: No. Routine reactions and emoji do not need rewriting; reserve the workflow for messages where outcome matters.
- What if my real voice is curt by default?: Use the rewriter to add one warmth signal per message (a name, a thanks, an acknowledgment of context). Not corporate softeners.
- How do I handle group threads where multiple people might read it?: Write to the one person who has to take the action. The other readers will skim regardless.
- Can I use this for emails too?: Yes for short emails. Long emails (200+ words) need different scaffolding — closer to a memo than a Slack message.
Related
Tags: #slack #communication #Tutorial