Skip to content
Imagine
Book a demo

Comment early on the posts your buyers are reading

Keep a list of the people your buyers follow. A few times a week, ask the agent which of their posts are picking up comments fast, and leave a specific comment from you and one or two teammates in the first hours, when comments get the most views. The Imagine AI agent finds the posts and drafts each comment in each person's voice for approval.

Last updated
Oct 20, 2026
Written by
Sky Yang, Co-founder and CEO
How we wrote this
Written from how the Imagine AI agent runs this play on LinkedIn, with approval.
Book a DemoSee the free benchmark
When it runs

Someone your buyers follow has a post taking off.

One prompt. The agent runs the play.

The agent has its own computer and browser, so it finds the people and the news itself. It drafts every comment, connection note and message, and you approve what goes out. Use it when:

  • Your buyers read a handful of voices you can name.
  • Your posts reach peers, not buyers.
  • Teammates want to be visible but don't have time to scroll.
Posts taking off today
Fig. 01: Comment early on posts taking off, run by the agent. You approve before anything goes out.

The skills behind this play.

The agent has its own computer and browser, so it does the legwork itself. Every skill is on for every play; these are the ones this play leans on.

[01]Used in this play

Writes in each person's voice

Drafts for the company page, founders, executives and employees from each person's best posts. Imagine AI started as the operating system for ghostwriting teams, so sounding like you is the core of the product.

[02]Used in this play

Has its own computer and browser

It does the legwork itself: finds the people, checks job changes, launches and funding news, reads the sources and fact-checks claims before anything ships.

[03]Used in this play

Engages for you

Comments, connection requests and messages on LinkedIn, aimed at the people your posts pull in who match your ICP.

[04]On

Designs the graphics

Multi-image posts, infographics and visuals from your brand kit, made in its own sandbox, with the right people and companies tagged.

[05]On

Runs one calendar for the team

Plan launches, sequence posts, schedule comments and edit together. Approvals sit with each person or route through one owner.

[06]On

Works from your content filesystem

Positioning, brand kit, decks, campaigns and compliance rules in one place it reads before every draft, remembered across threads.

[07]On

Turns what you have into posts

Events, podcast episodes, videos, decks and call notes become a week of posts across the team.

[08]On

Knows what works

Reads the public benchmark of 1,000+ B2B companies and tracks your competitors, so post types and formats follow your industry's data.

[09]On

Finds the buyers in your audience

Matches everyone who engages to your ICP and hands sales a worked list every week.

[10]On

Maps content to revenue

Connects to HubSpot or Salesforce and traces each closed deal back to its first content touch: post, person, deal stage moves.

[11]On

Plugs into your stack

Engager data over API and webhooks, and the benchmark over MCP for your own agents.

Step by step

The playbook lives as a file the agent reads. Edit it once and every run follows it.

What you need
  • A list of 20 to 50 people your buyers follow.
  • Which teammates comment, and how each one sounds.
  • One or two things you know that most people don't.
Files/Imagine AISend to agent

viral-post-pile-in.md

Save

Step 1 · Build the list

  • 20 to 50 people your buyers follow: analysts, operators, founders in your space. The agent can suggest names from who your ICP engages with.

Step 2 · Check what's taking off

  • A few times a week, ask the agent which posts from the list are picking up comments fast. It reads the post and the top comments.

Step 3 · Draft one useful comment each

  • One specific comment per person, adding a number or an example. Different angles from each teammate, never the same line twice.

Step 4 · Approve and post early

  • Comments posted in the first hours sit near the top. You approve each one, then it goes out from the right profile.

Fig. 02: The playbook as a file in your workspace.

Anatomy of a comment that gets read

The outline, what to avoid and how to measure it, in the file the agent drafts from.

Files/Imagine AISend to agent

comment.md

Save

Outline

  • 1Agree or disagree in the first five words.
  • 2One number or example the post doesn't have.
  • 3No links and no mention of your product.

Example from the run above

  • We saw the same split in our data: founders' posts get about 1.7x the company page. The gap is bigger in fintech.
  • The hiring point is underrated. Our best posts this quarter were about one person who joined, not the role.
  • Agree on shipping in public. The changelog posts we almost didn't write did better than the launch.

Avoid

  • "Great post!" and other comments that could go anywhere.
  • Three teammates making the same point.
  • Dropping a link to your own content.

Measure

  • Profile views from comment days.
  • Replies to your comments from the author.
  • Connection requests from people in your ICP.

Fig. 03: The outline, part by part.

Join the high-growth companies already building with Imagine AI

Questions teams ask first.