Find relevant posts in your niche, draft contextual comments that add real value, and surface high-engagement threads worth joining. Most LinkedIn growth tools post for you and get you flagged. This finds the right rooms and lets you say something worth reading.

This is the whole blueprint, nothing held back: the model, the tools, the exact prompt, the source on disk, and the setup. Everything you need to run LinkedIn Engager yourself is on this page, and it deploys in an afternoon.

What it does

LinkedIn Engager handles the work end to end:

Find recent posts in your niche by keyword and target authors
Rank threads by engagement velocity in their first 6 hours
Draft 1-3 sentence comments that add a specific data point or counter-take
Output a daily review digest so humans approve before posting

The anatomy

An agent is a composition, not a prompt: a model, the tools it is allowed to call, the integrations that give those tools reach, and the rules that keep it honest. Here is LinkedIn Engager on one card.

LinkedIn Engagerblueprint

Model: claude-sonnet-4-6
Tools: find_relevant_postsrank_threadsdraft_commentsurface_top_threads
Integrations: Browser UseZod
Guardrails: comments must be 1-3 sentences. never longer.; never start with "great post!" or any generic affirmation

The instructions

Every run is governed by this prompt. It is short on purpose: enough to make LinkedIn Engager reliable, not so much that it can misread itself. Copy it as a starting point for any agent you build.

LinkedIn Engager

You are a LinkedIn engagement strategist. You build presence by adding real value, not by spraying generic compliments. WORKFLOW: 1. Call find_relevant_posts in the user's niche by keywords and target authors. 2. Call rank_threads by engagement velocity (comments per hour in first 6 hours). 3. Call draft_comment that adds a specific data point, counter-take, or question. 4. Call surface_top_threads daily as a digest the user reviews before posting. RULES: - Comments must be 1-3 sentences. Never longer. - Never start with "Great post!" or any generic affirmation. - Always reference a specific line from the post, not a paraphrase. - Refuse to draft on posts older than 24 hours.

The source, on disk

Three files carry the whole agent: the definition with its tools, the environment it expects, and the setup. Walk them.

linkedin-engager/linkedin-engager.ts1.2 KB

1import { agent, tool } from "@agent-sdk"

2import { z } from "zod"

4const findInput = z.object({

5 keywords: z.array(z.string()).min(1).max(10),

6 authors: z.array(z.string()).optional(),

7})

9export default agent({

10 model: "claude-sonnet-4-6",

11 permissionMode: "bypassPermissions",

12 maxTurns: 20,

13 systemPrompt: `...`, // see System Prompt section above

14 tools: {

15 find_relevant_posts: tool({

16 description: "Surface recent posts by keyword and author",

17 inputSchema: findInput,

18 execute: async ({ keywords, authors }) => { /* Browser Use */ },

19 }),

20 rank_threads: tool({

21 description: "Score threads by comments-per-hour velocity",

22 inputSchema: z.object({ posts: z.array(z.any()) }),

23 execute: async ({ posts }) => { /* ranked */ },

24 }),

25 draft_comment: tool({

26 description: "Draft a 1-3 sentence value-add comment",

27 inputSchema: z.object({ post: z.any() }),

28 execute: async ({ post }) => { /* string */ },

29 }),

30 surface_top_threads: tool({

31 description: "Output daily digest for human review",

32 inputSchema: z.object({ ranked: z.array(z.any()) }),

33 execute: async ({ ranked }) => { /* digest markdown */ },

34 }),

35 },

36})

The business case

If you run an agency, LinkedIn Engager is also a product. It sells into founder-led marketing, personal brands, b2b operators, and the numbers work at very small scale.

$2,200

setup you can charge

$380/mo

monthly retainer

jobs off your plate

Ship it

The whole install is a handful of commands and the keys from the env file. Run the list, then point LinkedIn Engager at real work.

Deploy checklist

0 of 4

That is the entire blueprint: one model, 4 tools, and a prompt. Built by hand it costs you an afternoon. Inside Ultron it costs you a sentence, because you can build this exact agent in the workforce and watch it run before you commit to anything.

Build LinkedIn Engager in Ultron

Describe what you want

Start from this blueprint or your own words. Ultron reads the intent and picks the tools.

It builds the agent

The model, the tools, the prompt, the console. Assembled in front of you, nothing to wire.

Watch it run

Test it live in the chat, then put it to work. You review what it does, it does the rest.