Hire an AI task follow-up and voice editor

Everything it can hand back

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

• One follow-up draft per due task, with To, CC, subject, body, task ID and thread ID
• A draft ledger with each draft's version, state and message ID
• The same drafts edited to your voice, each fix shown before and after
• A list of missing facts, tasks with no recipient, and drafts waiting for your yes

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

• Generic copy that could fit any brand.
• Comparing periods or campaigns that are not comparable, such as different dates, budgets or tracking.
• Calling a test winner before there is enough data.

What a good result looks like

An example, not your task: Several tasks are past due or due this week, and each one needs an email to chase or confirm.

• follow-up-drafts.md. One draft per task, with task ID, thread ID, To, CC, subject and body.
• draft-ledger.csv. Each draft's version, state and message ID, so a rerun does not double send.
• Missing facts and pending approvals. Tasks with no thread or recipient, and drafts waiting for your yes.
• Edited drafts. The same drafts with off-brand words fixed. Claims and facts are left alone.

How the work is checked

• Every claim traces to the brand brain or supplied evidence.
• Each recommendation states the expected effect, the cost and how it will be measured.
• Copy fits the platform's length limits and the brand voice.
• 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 would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Draft the follow-ups. Picks the tasks due in your window, matches each to its thread and recipient, and writes one email draft per need. Logs each draft by task and thread, and lists missing facts.
• Check them against your voice. Reads the drafts from step 1 against your voice notes or past emails. Flags each off-voice line with a before and after fix. Facts and recipients stay as step 1 set them.

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 draft-your-due-task-followups 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/draft-your-due-task-followups/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

• Your task list or action register, with due dates, owners and status
• The email threads that match each due task, or an export you can paste
• The date window to cover, such as this week
• Your voice notes or a few past emails (optional)

Functions and deliverables

• Task follow-up and voice editor: Match due tasks to real threads and recipients, draft the needed follow-ups and edit wording using your supplied voice rules.
  • One follow-up draft per due task, with To, CC, subject, body, task ID and thread ID
  • A draft ledger with each draft's version, state and message ID
  • The same drafts edited to your voice, each fix shown before and after
  • A list of missing facts, tasks with no recipient, and drafts waiting for your yes
• Task follow-up writer: Share dated tasks and their message threads. Get recipient-specific follow-up drafts, missing facts and a clear draft/sent status.
  • follow-up-drafts.md with task ID, thread ID, recipients, subject and body for each draft
  • draft-ledger.csv with the version, state and message ID of each draft
  • A list of missing facts and approvals you still need to give
  • A short close with source coverage and one next step
• Draft brand voice checker: Share a draft and voice guide. Get ranked findings and before-and-after edits for top issues.
  • Issues ranked High, Medium or Low
  • The reason each line was flagged
  • A before and after fix for the top issues
  • A separate list of legal and compliance flags
  • A short overall verdict
  Source: Anthropic.
• Email call to action editor: Paste your draft and get a clearer email with one ask, a date and a reason in the first three lines. Edit a work email before you send it.
  • Every ask in your draft, counted and quoted
  • The rewritten email with the ask, date and reason in the first three lines
  • The parked asks and where they go
  • The word count before and after
• 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

Tasks you can use it for

• Several tasks are past due or due this week, and each one needs an email to chase or confirm.
• You have a task list and the threads behind it, and you want drafts to review, not a blank page.
• You want a record of which follow-ups were drafted, approved and sent, so a rerun never sends twice.

Limits to check before starting

• You want to chase late invoices: use the Payment reminder letter writer.
• You want a stalled sales lead nudged: use the Sales follow-up email writer or the Follow-up email sequence writer.
• You want one reply to an upset customer: use the Angry customer reply writer.
• You start from meeting notes, not from tasks that are already due: use Meeting action follow-up writer.

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.

• Add the skill pack to your AI. It is HANDOFF.md plus one skill file for each step.
• Share your task list and the email threads, and name the date window.
• Add your voice notes or a few past emails if you have them.
• Ask it to follow HANDOFF.md and mark missing facts.
• Read each draft. Approve the ones you want sent. Nothing goes out until you say so.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/draft-your-due-task-followups 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.