LinkedIn DM generator

The first message to a new connection, or the follow-up after a call, a conference, or a long silence. Describe the situation and who they are, and get three messages of two to four sentences that reference the real context, move the conversation one honest step, and make replying easy. No 'just checking in', no pitch disguised as a question.

Fill in what you have. More context, better output.

Tone
Message type

A small set from the tones and types inside Depost AI, where the analytics also show which ones land with your audience.

Free, no account. What you type is sent to our API once, to generate the result, and is not stored.

Result

This is the shape of what comes back. Fill in the form, or hit "Try an example", and the grey turns into words.

Example run

Three follow-ups after a new connection

Three ways to follow up without pitching. The first line references the shared context, and none of them corner the reader into a reply they do not want to write.

What went in

The situation
She accepted my connection request yesterday after commenting on my post about onboarding emails.
Who they are
Lifecycle marketer at a consumer fintech app.
Where the conversation should go
A relaxed exchange about onboarding flows; if it goes well, I would show her our tool.
Tone
Casual
Message type
Thanks

What came back

Message 1 · Plain thanks

Atta Ur Rehman Shah

Thanks for the comment on the onboarding emails post. Your point about timing the second email off behavior instead of a fixed delay was the sharpest take in the thread. Glad to be connected.

Message 2 · Callback

Atta Ur Rehman Shah

Appreciated your comment yesterday. You mentioned testing send times by behavior, did that come out of your work at the app? Would genuinely like to hear how it played out.

Message 3 · No ask

Atta Ur Rehman Shah

Good to be connected. Your comment made me rework a section of that onboarding post before I reuse it in a talk, so thank you for that. No agenda here, just glad the feed surfaced someone working on the same problems.

Why it matters

DMs convert when the sender is visible.

LinkedIn gives a direct message more room than anyone should use. What earns the reply is the sender: a specific reason for writing, from a profile that has been showing up.

8,000

characters allowed per message. The ones that get answered use a couple of hundred.

LinkedIn limit

7×

higher conversion for leads generated through employees’ social media.

IBM

82%

of people are more likely to trust a company whose senior executives are active on social media.

Entrepreneur

Not our numbers. IBM’s and Entrepreneur’s.

Beyond the demo

This page writes from a form. The product writes from you.

The generator above works with whatever fits in a few fields. Connect LinkedIn to Depost AI, the AI content team B2B founders and teams run on LinkedIn, and the same kind of draft starts from your analytics, your voice, and the buyers you are actually trying to reach.

Drafts that start from your analytics

The agents read your posting history first: the hooks that earned the click, the pillars your audience answers, the rhythm of what worked. The draft sounds like you because it learned from you, not from a form.

A reply ready for every person who matters

Build custom lists of the people you want to stay visible to. Their new posts arrive in one feed with a comment drafted in your voice under each. You edit or approve every one before it goes anywhere.

From draft to published, without the paste

Finished drafts go to the queue and publish through LinkedIn’s official API, with the first comment written alongside. Connection notes and follow-ups are drafted with the context already in place. Nothing goes out until you approve it.

Connect LinkedIn and you have a strategy, your pillars, and your first post ideas in about fifteen minutes.

The situation is the message

Generic DM advice fails because there is no generic DM. The right first message to someone who commented on your post yesterday shares nothing with the right note to someone you met at a conference in March, and both differ from the follow-up after a call that went well. That is why this tool leads with the situation field instead of a dropdown of message types: describe what actually happened, and the message can be about that. It is how the best B2B relationships read in the DMs: two operators comparing notes, not a sequence step firing on schedule.

The common thread across situations is direction. A good message moves the relationship one step: from accepted to talking, from talked-once to talking-again, from talking to meeting. One step. The messages that die unread are the ones that try to travel the whole distance at once, which is what a pitch in message one is.

Make replying cheap

People answer messages that are easy to answer. One clear question beats three, a question about their experience beats a request for their time, and sometimes no question at all ("no reply needed, the talk was just genuinely useful") is the most disarming move available, because it proves you want nothing. The generator ends each message accordingly.

And read the reply you get. The failure mode of tool-assisted outreach is not bad messages; it is not listening to the answers. The generator gets you into the conversation. Being worth talking to once you are there was always your job.

Questions

What should I say in a first message to a new LinkedIn connection?
Reference the thing that connected you, add one honest sentence about why you are glad it did, and either ask one easy question or ask nothing at all. What you should not do is pitch, because a pitch in the first message tells the person the connection was a pretext, and they will read every later message through that. The generator writes for the situation you describe, not from a sequence template.
How do I follow up without being annoying?
Bring something, or wait until you have something. A relevant article, a genuine reaction to their new post, an answer to a thing they mentioned: each is a reason to appear that costs the other person nothing. "Just checking in" and "bumping this" bring nothing and ask for attention anyway, which is the annoying part. Frequency matters less than whether each message carries its own weight.
How long should a LinkedIn DM be?
Two to four sentences. The message field technically allows 8,000 characters, and using even a tenth of that in a first message reads as a mail merge. Short signals respect for the other person's time and confidence that the conversation can develop; long signals a script. The generator stays in the two-to-four range by design.
When is it okay to bring up my product or service?
When the conversation has earned it: they asked what you do, or described a problem you genuinely solve, or you have exchanged enough that a straightforward "this is what we do, want a look?" is honest rather than sprung. The goal field lets you tell the generator where you hope things go, and it will move one honest step in that direction without jumping there.
Is it free, and is what I type stored?
Free, no account, with a daily cap so it stays available. The three fields are sent once to generate the messages and are not stored.
How do I keep up with more than a handful of relationships?
Not from memory. The message is the easy part; knowing who to message, and when, and about what, is what falls apart at fifty people. Depost AI keeps your people in custom lists, surfaces their new posts as reasons to reach out, and drafts the reply in your voice, so consistency stops depending on your calendar being quiet.

Make LinkedIn your
best-performing channel.

Brief your team once. It studies, plans, writes, designs, and schedules. You approve.

Your brief comes with you: once you're set up, it's the team's first job.

7 days free · Strategy in your first 15 minutes · Cancel anytime