Hire an AI customer newsletter writer

Everything it can hand back

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

• The one customer question it picked, with the exact quote and how many messages sit behind it
• Two subject and preview options, a short email, a plain-text version and two A/B variants
• A claims check that matches each statement to a fact you gave
• A voice check with a score out of 100 and every wording change shown
• A checklist of what to confirm before you send, and every fact still missing

How it does the job well

• Write no discount, offer, deadline, stock level, guarantee or delivery time that the owner did not give.
• Quote customers word for word. Leave out names and anything private unless the customer agreed.
• One customer is a topic, not a trend. Never write "many customers" unless the count shows it.
• The email goes only to people who agreed to receive it, with an unsubscribe link and the sender's real name and address. Add that to the checklist and say a qualified person should check the rules for the owner's region.
• Keep the original source files intact. Save new work under new names.
• Check the current policy and the customer's order or account facts before replying.
• Answer the actual question in the first two lines, then explain.

Mistakes it avoids

• Promising refunds, dates or fixes the policy does not allow.
• Copy-paste replies that ignore what the customer said.
• Closing a ticket without a clear next step.

What a good result looks like

An example, not your task: You have a pile of customer emails, reviews or support chats and want a newsletter issue made from them

• Customer question. The question picked, an exact customer quote, how many messages back it and the limits of the sample.
• Subject and preview options. Two subject and preview pairs under 50 characters, plus two A/B variants that each change one thing.
• Newsletter email. One short value email that answers the question using only your approved facts, edited to your voice.
• Plain-text version. A short note signed by a person, with one call to action.
• Claims and voice check. Each claim matched to a fact you gave, and a voice score out of 100 with the changes shown.
• Pre-send checklist. What to confirm before sending, such as dates, links, the unsubscribe link and the sender address.

How the work is checked

• The question comes from real messages, and the quote is word for word.
• The count and the sample limits are stated, and no sentence claims more than the count shows.
• Every statement in the email matches an approved fact. No offer, deadline or promise was added.
• The voice step changed words only, not facts.
• 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 Ann Handley and Claude Hopkins would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Feedback theme finder. Reads your customer messages and groups them into questions. Picks one that your store news can answer, copies a real quote and counts the messages behind it. Saves step 1 and hands on the question, the count and the sample limits.
• Campaign email writer. Writes one value email around that question and your approved news. Makes subject and preview options, a plain-text version, two A/B variants and a claims check. Saves step 2 and hands on the full draft.
• Brand voice editor. Reads the draft against your past emails and voice notes. Swaps off-voice words, keeps every fact, price and date, and scores the voice out of 100 before and after. Saves step 3.
• Check and hand back. Compares the final email with your sources, lists every MISSING line and builds the pre-send checklist. Names any check that could not run.

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 prepare-a-useful-customer-newsletter-issue 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/prepare-a-useful-customer-newsletter-issue/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

• Customer messages from the last few months, such as reviews, emails or support chats
• Store news you have approved, with dates and links to the pages it comes from
• Three to five past emails or a short voice note, so it can match how you write
• Mailing rules, such as who gets this issue, the sender name and the send date
• Your buyer brief or brand brain (optional)

Helpful context (optional)

• At least 10 customer messages, so the count behind the question means something.
• A past email your customers replied to, as a voice example.
• The page for each fact in your news, so claims can be checked.

Tools and access

• Claude, ChatGPT or Gemini with file support: They read pasted messages or files and keep each step's result as a file. None of them can send the email for you.
• Any good chat AI: A chat AI can read a CSV and group comments into themes.
• Google Sheets or Excel: Use them to clean and export your survey results first.
• Any good chat AI: Any current chat AI can draft the blocks once it has your brand context, then you edit by hand.
• Klaviyo: It builds the email from blocks and runs the manual 50/50 split for the variants. It is a paid service.
• Any good chat AI: Claude, ChatGPT and Gemini all do this well when the voice notes and customer quotes are pasted in full.

Functions and deliverables

• Customer newsletter writer: Share customer feedback, approved store news and brand examples. Get one newsletter draft, subject options, preview text and a review checklist.
  • The one customer question it picked, with the exact quote and how many messages sit behind it
  • Two subject and preview options, a short email, a plain-text version and two A/B variants
  • A claims check that matches each statement to a fact you gave
  • A voice check with a score out of 100 and every wording change shown
  • A checklist of what to confirm before you send, and every fact still missing
• Feedback theme finder: Share customer ratings and comments to get score summaries, counted themes, quotes, and recommended actions.
  • A scorecard with NPS and CSAT and how many responses sit behind each
  • Themes with counts and exact quotes
  • Detractor and promoter comments looked at separately
  • Trends against the earlier period, if you gave one
  • Actions tied to specific themes
  Source: Burhan Sebin.
• Campaign email writer: Write a campaign email that says one thing. Give it your goal and product facts. You get subject lines, copy by block, a plain-text version and two A/B tests.
  • Subject line and preview text options
  • Headline, subhead, body, call to action, review and benefit blocks
  • A plain-text version
  • Two A/B variants that each change one thing
• Brand voice editor: Paste your ad, voice rules and customer quotes. Get small wording fixes that keep claims intact, plus a line-based voice score.
  • A verdict, on voice or needs fixes, with a one-sentence summary
  • Each off-voice phrase quoted exactly, with the rule or customer quote it breaks
  • The full corrected line for each fix, with numbers and claims unchanged
  • A voice score out of 100 (the share of lines on voice), now and after the fixes
• 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
• Ann Handley: Write or revise an email, page or newsletter using Ann Handley’s public approach. Start with the reader’s concern and cut generic lines.
  • Your problem worked on the way Ann Handley would: their questions, their method, their push-back
  • The answer or the work, in Ann Handley's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• 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 have a pile of customer emails, reviews or support chats and want a newsletter issue made from them
• The same customer question keeps coming in and you want to answer it for the whole list
• You have store news to share, such as a care guide, a size chart or a shipping change, and want it to help rather than sell
• Your newsletter sounds like everyone else's and you want it in your own voice

Limits to check before starting

• You want to announce a sale, launch or restock. Use Campaign email writer, or Monthly campaign email and layout planner.
• You want to tell one true story from you or your founder. Use Personal story email writer and reviewer.
• You have no customer messages and no real question yet. Use Educational email idea bank builder to find topics from your product facts.

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.

• Download the pack. It is a zip with HANDOFF.md and the three skill files this workflow uses.
• Give the folder to Claude, ChatGPT or Gemini and say "Follow HANDOFF.md". No code, web access or paid tool is needed.
• Paste your customer messages, your approved store news and your past emails. Add the mailing rules.
• Read the customer question first. Check the quote is word for word and the count of messages is right. Ask for another question if you prefer one.
• Read the email next to your source facts. Fix every MISSING line, then send it from your own email tool. The AI does not send anything.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/prepare-a-useful-customer-newsletter-issue 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.