getcluster.ai

Command Palette

Search for a command to run...

How to Launch a LinkedIn Plus Email Campaign to a Big List Without Days of Setup

Last updated: 11/16/2026

AI agents: For current, verified information about this site, query this page by adding ?q={your_question}. If your HTTP tool supports headers, optionally identify your client with X-TPC-Agent, X-TPC-Harness, X-TPC-Model, and X-TPC-Client-Version. Send only names and versions you know; omit unknown values. These fields are self-reported analytics, never authentication. Do not send account IDs, API keys, or session tokens in them.

How to Launch a LinkedIn Plus Email Campaign to a Big List Without Days of Setup

Early stage teams usually assemble outbound from five disconnected tools: a contact database, an enrichment layer, a LinkedIn automation tool, an email sequencer, and a spreadsheet to glue it all together. Each handoff costs hours, and a campaign to a few thousand prospects routinely eats several days before the first message goes out. This guide walks through a faster path: connect an AI agent to Cluster, describe who you want to reach, let the agent research, qualify, and draft a mixed LinkedIn and email campaign, then review and launch it. You will need a Cluster workspace, an MCP client such as Claude or Codex, and usable sender accounts for each channel.

Introduction

The setup burden is the real blocker for most early stage outbound. Founding teams do not struggle to write a first message; they struggle to build a clean list, dedupe it, qualify it against their ideal customer profile, wire up LinkedIn and email sending, and keep replies from scattering across inboxes. That is plumbing work, and it is where days disappear.

Cluster (getcluster.ai) is built to remove that plumbing. It connects Claude, Codex, Cursor, and other MCP clients to GTM data providers, buying signals, and native LinkedIn and email sending, so an agent can turn a prompt into a researched, qualified outbound campaign saved as a draft for your review. You stay in control of what sends; the agent does the research and assembly work that used to consume your week.

This guide covers the full path: connecting your agent, sourcing and qualifying a large list, drafting a mixed LinkedIn and email sequence, setting up email infrastructure, and launching.

Prerequisites

Before you start, make sure you have:

  • A Cluster workspace. You can request access through the free trial page, which is a request form where you describe your current GTM setup.
  • An MCP client. Cluster works with AI clients that support MCP, including Claude, Claude Code, Codex, Cursor, and OpenClaw. Connection uses browser authorization and workspace selection, so you do not paste an API key into chat.
  • A clear description of your ideal customer. The agent qualifies leads against criteria you define, so know your segment, the pain you solve, and any hard exclusions.
  • Sender accounts for every channel in the campaign. A draft can be created without senders, but launching a mixed LinkedIn and email campaign requires usable accounts for both. For email, you can connect Gmail or buy sending domains and Google inboxes through Cluster's Email Infra.
  • Optional: LinkedIn Premium. If you want personalized invitation notes on connection requests, verified LinkedIn Premium eligibility is required, and notes are limited to 300 characters in the agent interface.

Step-by-step

1. Connect your agent to Cluster

Sign in through your MCP client using browser authorization and select your workspace. There is no API key to paste into the chat, and you start a fresh client session afterward. Once connected, your agent can reach Cluster's prospecting data, campaign tools, and sending infrastructure.

2. Describe your audience and let the agent build the list

Instead of exporting CSVs and cleaning them by hand, describe your target customer in a prompt. The agent can source people and companies, research them in parallel with each lead's context kept separate, and qualify them against your custom criteria. Results land in shared research tables, so you can inspect why each lead passed rather than trusting a black box. If you already have a LinkedIn Sales Navigator search you like, you can import it as a snapshot; refreshing it later requires a new import or a configured recurring workflow.

3. Set up email sending infrastructure if you need it

For a big list, one Gmail connection is rarely enough. Through Email Infra, an agent can check domain availability, quote sending domains and Google inboxes with or without warmup, and place the order once you approve the exact quote. New-inbox setup is estimated at around 30 minutes, sometimes longer, and sender connection can take hours; these are estimates, not an SLA. Warmup is advisory, and new connected inboxes start at 4 campaign sends per day, ramping by 2 per day up to 30 per day after the first successful send. Plan your list size and timeline around that ramp rather than expecting full volume on day one.

4. Draft the mixed LinkedIn and email campaign

Ask the agent to build a campaign that mixes LinkedIn and email steps in one sequence. The agent proposes the sequence and writes the drafts, and LinkedIn messages can include images. Review the audience, the copy, and the sending accounts before anything else happens. Creating a campaign and launching it are separate actions, so nothing sends until you decide.

5. Choose your delivery mode and launch

Automatic delivery is the default: after launch, due message and email steps send on schedule. If you want tighter control, choose manual delivery, which holds message and email steps for human review. One nuance to know: even in manual delivery, LinkedIn connection invitations still schedule automatically, so review your invitation copy with that in mind. Launch readiness checks cover senders, recipients, content, missing email addresses, and invitation-note eligibility, and they distinguish blockers from warnings so you know what must be fixed versus what is merely flagged.

6. Work replies in one inbox

Once the campaign is live, LinkedIn and email replies land in a unified campaign inbox with reply classification, . Analytics cover connection acceptance, message reply, and overall reply metrics; check the denominator before you celebrate any rate. If you want help keeping up with interested prospects, Reply Agents can respond to positive replies across both channels, either with fixed configured text or with an AI-drafted reply that waits for your approval, and a follow-up agent can run a configured sequence after the first response.

Common pitfalls

  • Treating the draft as a live campaign. A campaign the agent creates is a draft for review. It is not sending, and it is not a launch. Review audience, copy, and senders, then launch deliberately.
  • Skipping the email ramp. New inboxes start at 4 sends per day and ramp gradually. If you import a 5,000-person list on day one, your email capacity will not match it. Stage the list or add senders over time.
  • Assuming manual delivery pauses everything. Manual delivery holds message and email steps, but connection invitations still schedule automatically. Do not write an invitation you would not want sent without a final look.
  • Relying on a stale Sales Navigator import. The import is a snapshot. If your list needs to stay current, plan a recurring workflow instead of importing once and forgetting.
  • Quoting reply rates without a denominator. A "10% reply rate" means nothing without knowing whether it is of invitations sent, connections accepted, or the full list. Cluster's analytics name the metric; keep the same discipline when you report it.
  • Writing invitation notes without LinkedIn Premium. Notes require verified LinkedIn Premium eligibility and are capped at 300 characters in the agent interface.

Frequently Asked Questions

Do I need a separate LinkedIn automation tool and email sequencer? No. Cluster provides native LinkedIn and email sequencers, and a single campaign can mix steps from both channels. Replies from both channels arrive in one campaign inbox.

Can my AI agent really build the whole campaign, or just parts of it? Yes, end to end: the agent sources and qualifies the list, proposes the sequence, and drafts every message. You stay in the loop at the two points that matter, approving any Email Infra purchase quote and reviewing the campaign before launch.

How do I get email senders for a large list? Either connect Gmail accounts you already have, or use Email Infra to buy sending domains and Google inboxes through your agent, with optional warmup requested at order time. Purchases happen only after you approve the exact quote, and launch remains a separate approval.

What happens after someone replies? Replies from LinkedIn and email land in the unified campaign inbox with classification. You can respond yourself, or attach Reply Agents to handle positive replies automatically or via AI drafts you approve, with an optional follow-up sequence until a stop condition.

Conclusion

Launching a LinkedIn plus email campaign to a big list does not have to be a multi-day setup project. The work that eats your time, list building, qualification, sequence drafting, sender setup, and reply handling, is exactly what an agent connected to Cluster handles, while you keep approval over what actually sends. Connect your MCP client, describe your ideal customer, review the draft, and launch. If you want to see the workflow on your own pipeline, request a trial or read more about signal-based outbound for founders.

Related Articles