Skip to content
Imagine

Fill your conference week from LinkedIn

Two weeks out, find the people in your ICP posting about the event and connect with a short note. A week out, post that you're going and what you want to talk about, and ask the best fits for coffee. After the event, post a recap that tags the people you met and send each a follow-up the same week. The Imagine AI agent finds the people and drafts every post, note and message 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.
When it runs

You're going to a conference your buyers attend.

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 go to a few events a year and post about them.
  • Your conference meetings come from luck in the hallway.
  • Follow-ups after events slip a week and go cold.
SaaStr week
Fig. 01: Conference before and after, 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]Used in this play

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.

[05]Used in this play

Finds the buyers in your audience

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

[06]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.

[07]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.

[08]On

Turns what you have into posts

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

[09]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.

[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.

What the data says

Event beats the author's typical post in 5 of 13 industries, median 0.98x.

  • Healthcare Tech23.5% of posts1.14x
  • Tax & Accounting22.5% of posts1.13x
  • Security & Compliance24.4% of posts1.07x
  • Venture Capital20.9% of posts1.07x
  • Data & Analytics30.2% of posts1.02x
  • Fintech20.7% of posts0.99x
  • Dev Tools & Infrastructure19.9% of posts0.98x
  • Sales & Marketing Tech17.1% of posts0.98x
  • Other B2B SaaS15.8% of posts0.98x
  • HR & Payroll21.5% of posts0.97x
  • Voice & Media AI19.7% of posts0.95x
  • AI Infrastructure19.4% of posts0.93x
  • Customer Support AI19.7% of posts0.92x
Fig. 02: Event by industry, dashed line at 1x. Source: Imagine AI Benchmark (benchmark.useimagine.ai), public aggregates, data through Oct 20, 2026. Lift = a post type's reactions as a multiple of each author's own typical post (geometric mean), so big accounts do not skew it. CC BY 4.0.

Step by step

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

What you need
  • The event name and hashtag.
  • Your ICP, to filter who is posting.
  • What you want to talk about there, in one line.
Files/Imagine AISend to agent

conference-before-and-after.md

Save

Step 1 · Find who's going

  • Two weeks out, people in your ICP who posted about the event, with speakers and sponsors flagged.

Step 2 · Connect before

  • A connection request that mentions the event and their talk or post.

Step 3 · Post that you're going

  • A short post a week out: you'll be there, the one thing you want to talk about, and a question to the room.

Step 4 · Ask for coffee

  • A message to the best fits with a specific time slot. Specific times get more yeses than "let's meet".

Step 5 · Recap and follow up

  • After the event, a recap post that tags the people you met, then a follow-up to each within the week, logged in your CRM.

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

Anatomy of the coffee ask

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

Files/Imagine AISend to agent

coffee-ask.md

Save

Outline

  • 1Both of you are at the event.
  • 2One specific time and place.
  • 3One reason you want to talk to them in particular.

Example from the run above

  • Saw you're speaking on the pricing panel at SaaStr. I'll be there too, would love to say hi.
  • Hey Marcus, both at SaaStr next week. Coffee Wednesday morning? I'd like to hear how you're hiring for growth.
  • Heading to SaaStr next week. I want to talk to anyone measuring which content brings in pipeline. Who else is going?

Avoid

  • Messaging after the event starts, when calendars are full.
  • A recap post that only thanks your own team.
  • Following up two weeks later.

Measure

  • Meetings booked before the event.
  • Engagement on the recap from the people tagged.
  • Follow-up replies in the week after.

Fig. 03: The outline, part by part.

Join the high-growth companies already building with Imagine AI

Questions teams ask first.