Hire an AI cold email batch writer

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• The call this week on what to fix, change or keep, with the numbers behind it
• A batch of cold emails that passed the claim check, in a table
• Follow-ups for people who have not replied, with timing
• Replies sorted, with drafts for the ones worth answering
• A log line and a do-not-contact list kept up to date

How it does the job well

• Write for one named audience and one action. Each asset has a single job.
• Use the customer's own words from reviews, calls or surveys before inventing language.
• Every claim needs proof the business can show. Leave unproven claims out or mark them.
• Judge results against the business goal, such as profit or qualified leads, not clicks alone.

Mistakes it avoids

• Sending, even when a mailbox is connected.
• Changing the list, the angle and the offer in the same week. You cannot tell which one worked.
• Judging a batch of ten emails.
• Making up a reason a prospect fits.
• Writing an email that works as a template with a name swapped in.
• Generic copy that could fit any brand.

What a good result looks like

An example, not your task: You send cold emails every week and want each batch to learn from the last.

• The call this week. The path chosen, such as fix setup, change angle or tighten list, with the numbers behind it.
• Batch. A table of prospect, subject, body and check result, with only emails that passed.
• Dropped. Each prospect removed from the batch and the reason.
• Follow-ups due. Who needs which touch, the send date and a draft.
• Replies. Each reply sorted by type, with drafts for positive and not now ones.
• Setup changes to approve. Any change to mailbox, domain or volume that needs your yes.

How the work is checked

• No email states a fact about a prospect that is not in the list or the supplied text.
• Every email has one ask and the sender details.
• Nobody on the do-not-contact list is in the batch.
• A batch after a bounce or complaint path was not written.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

A second opinion

Before it hands back, your AI reviews the draft the way Claude Hopkins would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Read the folder. Loads your offer, voice, log and do-not-contact list. On the first run it builds them from what you give it.
• Choose the path. If emails bounced or drew complaints, it stops and fixes the setup. If replies are low it changes the angle. If replies are not positive it tightens the list.
• Fill the list. Tops up prospects only when needed, keeping those with a stated reason and removing anyone already contacted or opted out.
• Write the emails. Writes in your voice if it has samples, each tied to a fact about the person. Follow-ups go to those who did not reply, up to four touches.
• Check and loop. Tests every claim against the text you supplied. A failed email is fixed and checked again, up to three rounds, then dropped.
• Sort replies and log. Sorts replies, adds unsubscribes to the do-not-contact list at once, drafts answers to the worthwhile ones, and logs the batch.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id cold-outreach-batch-runner only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/cold-outreach-batch-runner/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• Who you write to and what you offer, with the one ask
• Any result or client you can state as true
• Your prospects, each with a fact about them and where it came from
• Last batch's numbers, meaning sent, bounced, replied and positive replies
• A few emails you have sent and liked (optional)

Helpful context (optional)

• A short list of results or clients you can name
• Your last two batches' bounce and reply numbers

Tools and access

• Claude Code: It can keep the outreach folder, read the log and prepare a batch each week.
• Your mailbox or sending tool: Export bounces and replies from here. You send the approved emails yourself.

Functions and deliverables

• Cold email batch writer: Read the last batch's results, choose one supported change and prepare checked emails and follow-ups for you to review and send.
  • The call this week on what to fix, change or keep, with the numbers behind it
  • A batch of cold emails that passed the claim check, in a table
  • Follow-ups for people who have not replied, with timing
  • Replies sorted, with drafts for the ones worth answering
  • A log line and a do-not-contact list kept up to date
• Inbox delivery fixer: Share your sending domain. Get SPF, DKIM and DMARC checks plus a staged repair plan.
  • The SPF, DKIM and DMARC records to add
  • A staged DMARC rollout plan
  • A reputation monitoring routine
  • A list of likely causes of spam placement
  Source: RampStack.
• Prospect account researcher: Describe your ideal customer. Get matching accounts, fit reasons and verified contacts when available.
  • Qualified account list
  • Fit reason for each account
  • Contacts with an email status, verified only if you have a verifier tool
  • Tier or score for each lead
  Source: Corey Haines.
• Outreach writer in your voice: Share writing samples, prospects and your goal. Get email drafts and follow-ups shaped by your style and supported facts.
  • A saved voice profile
  • Emails with a real, specific hook
  • Follow-ups in your tone
  • Subject line options
  Source: Anthropic.
• Cold email writer: Share your buyer, offer and proof. Get a cold email, follow-ups and sending guidance.
  • Cold emails to send
  • Follow-up messages
  • Subject line options
  • Sending setup advice
  Source: Corey Haines.
• Outbound email sequence writer: Turn prospect details and your offer into email drafts with subject lines and suggested send timing.
  • A multi-step email series
  • Subject line options
  • Personal fields to fill in
  • A send schedule
  Source: Burhan Sebin.
• Cold email pre-send checker: Check your cold email before you send it. It tests claims about the prospect, checks legal basics and gives you a tighter version.
  • A claim-by-claim check
  • Legal basics notes
  • Flags on unproven statements
  • A tighter rewrite
  Source: Pro Skill Packs.
• Brand profile builder: Share your website. Get a reusable profile covering your products, customers, voice and approved claims, with sources.
  • A folder of eight plain files, from a start file for your AI to a claims list and a change log
  • A tag on every fact, and every claim marked approved, pending or banned
  • A two-sentence diagnosis of your biggest gap, and a list of what's missing and who can answer it
  • A short slice for your next step, if you name one
• Claude Hopkins: Write specific ads or plan a small buyer test using Claude Hopkins’s recorded approach. Replace vague praise with facts and track cost per customer.
  • Your problem worked on the way Claude Hopkins would: their questions, their method, their push-back
  • The answer or the work, in Claude Hopkins's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step

Tasks you can use it for

• You send cold emails every week and want each batch to learn from the last.
• Your replies are low and you do not know whether the list, the email or the setup is the cause.
• You want emails that sound like you, with no made-up facts about the person.

Limits to check before starting

• You have no offer, no proof you can state, or only a few dozen prospects: write and send those by hand.
• You want one email, not a weekly batch: use the Cold email writer.
• You want to send without reading each email: this agent never sends, and you must approve every one.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Start a chat with the agent. In Claude Code, add it as a skill or save it in .claude/agents, then ask it to prepare this week's batch.
• The first time, give it your offer, your proof, your sender details and your prospects. It saves them in an outreach folder.
• Paste last batch's numbers and any replies.
• Read the batch. Approve what you want and send it from your own mailbox.
• Run it again next week. It reads the log and changes one thing.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/cold-outreach-batch-runner for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.