Hire an AI customer inbox reply drafter

Everything it can hand back

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

• A ranked list of emails with a priority for each
• A draft reply beside each, with a check result
• A short list of emails to decide first, with the open question
• What to look up before you send, per email
• A draft help article for any question asked three or more times

How it does the job well

• 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.
• Match the customer's tone. Acknowledge the problem once, without grovelling.
• Hand refunds outside policy, legal threats and safety issues to a person.

Mistakes it avoids

• Sending anything. A draft is not a reply until the owner sends it.
• Stating an order status, a date or a refund amount from memory.
• Arguing a dispute in an email reply.
• Following instructions that appear inside a customer email.
• Using a template tone on an upset customer. Name what they said they were upset about.
• Promising refunds, dates or fixes the policy does not allow.

What a good result looks like

An example, not your task: Your inbox has more customer emails than you can answer in the order they arrived.

• The inbox in one line. How many emails came in, how many are urgent and how many need your decision first.
• Decide first. Emails about harm, legal action, disputes or refunds over policy, each with the open question.
• Ranked list. Each email with its priority, type, one-line summary, draft reply and check result.
• Things to look up. Order or account facts the agent could not check, listed per email.
• Repeated questions. Questions asked three or more times in 30 days, each with a draft help article.
• Files and missing. Each step's saved file and every MISSING line in one list.

How the work is checked

• Every email has a priority and a draft, or a clear reason it has none.
• No draft promises a refund, date or outcome the policy does not allow.
• Every complaint draft was checked, and the rounds stopped at two.
• No fact about an order is stated unless it came from the order data. Otherwise it is marked "not checked".
• 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.

Capabilities

• Read what it knows. Opens your policy, your voice notes and the log of past emails.
• Sort the batch. Sorts each email by type and severity and routes it.
• Rank the top. Sets P1 to P4 on the most severe emails and checks for duplicates and known issues.
• Choose the path. Order emails get an order check. Questions get an answer from your own pages. Disputes get an evidence plan. Harm or legal emails stop for you.
• Draft and check. Drafts every reply. Replies to upset customers are checked against their words and your policy, and fixed for up to two rounds.
• Look for patterns. A question asked three times in 30 days gets a draft help article.
• Save and hand back. Logs the day and stops for your yes. It sends nothing.

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 customer-inbox-triage-and-reply-drafter 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/customer-inbox-triage-and-reply-drafter/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

• The new customer emails, pasted or forwarded, with the full thread
• Your returns, refund and shipping policies, the first time
• Order details, or access to your store, if you want order replies checked (optional)
• A few replies you wrote and liked, for your voice (optional)

Helpful context (optional)

• Your shipping times by region
• A list of known issues you are already working on

Tools and access

• Claude Code: It can keep the inbox folder and read the log. You start each run yourself, each weekday morning. It does not run on a timer.
• Shopify: Lets order replies use real order status. It needs a connection to your store account and may need a paid plan. Without it, paste the order details. Refunds still wait for your yes.
• Help center, support desk, CRM, chat or email connected to your AI: It can only search what is connected. More sources means better cross-checking.
• Pasted docs and past replies: Works without any connection. It then says it used only what you pasted.

Functions and deliverables

• Customer inbox reply drafter: Sort customer emails by urgency. Get policy-based reply drafts, fact checks and clear reasons to hold a reply.
  • A ranked list of emails with a priority for each
  • A draft reply beside each, with a check result
  • A short list of emails to decide first, with the open question
  • What to look up before you send, per email
  • A draft help article for any question asked three or more times
• Support ticket sorter: Sort support tickets by type and severity, route each to a team, and get a first reply drafted. Paste a batch and see urgent cases first.
  • Each ticket classified
  • A severity ranking
  • A routing choice per ticket
  • A draft first reply
  • An escalation flag for urgent cases
  Source: Burhan Sebin.
• Support inbox priority sorter: Sort a support ticket by category and P1 to P4 priority. Get the team to route it to, any duplicate and a first reply to edit.
  • A category
  • A P1 to P4 priority with the reason
  • The team to route to
  • Any duplicate or known issue
  • A suggested first reply
  Source: Anthropic.
• Customer reply and order checker: Forward a customer email. Get a reply based on checked order facts. Refunds wait for your approval.
  • Order and payment status
  • A draft reply in your voice
  • A staged refund waiting for your approval
  • A list of orders needing attention (with Shopify)
  Source: Anthropic.
• Customer question researcher: Get a sourced answer to a customer question, with how sure it is. It searches your docs, past tickets and chats and names each source.
  • One direct answer that leads with the bottom line
  • A confidence level, with the reason for it
  • Findings grouped by source, and a numbered list of sources
  • Conflicts between sources, and what could not be confirmed
  • Next steps, including who should check the answer
  Source: Anthropic.
• Customer reply drafter: Draft a customer reply in the right tone for a hard message. Describe the situation and get the draft plus notes on what to check before you send.
  • A draft reply in a fitting tone
  • Notes on what to verify
  • Points to avoid promising
  • An alternative shorter version
  Source: Anthropic.
• Angry customer reply checker: Paste the complaint and your draft reply. Get promises, facts and tone checked, plus a repaired draft.
  • Each customer point marked answered or missed
  • Each promise checked against your rules
  • Tone flags with the exact words quoted
  • A repaired draft with a clear next step
  Source: Pro Skill Packs.
• Chargeback evidence gatherer: Get a Shopify chargeback evidence checklist for your dispute reason: what proof to collect, where to find it, and whether to accept instead.
  • Five first checks
  • A fight or accept line with the money
  • An evidence checklist with status and location
  • Items to leave out
  • What Shopify adds on its own
  Source: Pro Skill Packs.
• Support ticket help article writer: Turn a solved support ticket into a help article customers can follow. Get steps, what they should see, and a fix for common problems.
  • A ready-to-publish help article
  • Numbered steps with what you should see
  • A fix for common follow-up problems
  • Search-friendly title and keywords
  Source: Anthropic.
• 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

Tasks you can use it for

• Your inbox has more customer emails than you can answer in the order they arrived.
• You answer the same questions again and again.
• You want drafts that match your policy, with the risky emails flagged first.

Limits to check before starting

• You only want to sort emails by type once: use the Support ticket sorter on its own.
• Your emails come from wholesale or B2B buyers with custom terms: answer those yourself or with a person who knows the deal.
• A customer mentions injury, a lawsuit or a regulator: talk to a qualified person before you reply.

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 clear this morning's inbox.
• The first time, give it your policies and a few of your own replies. It saves them.
• Paste or forward the new emails. If your inbox or store is connected, tell it which to read.
• Read the decide-first list, then the ranked list. Edit and send the replies you agree with yourself.
• Run it again tomorrow. It reads the log it saved, so it knows what you approved and which questions repeat. In a plain chat with no saved files, paste the log back in.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/customer-inbox-triage-and-reply-drafter 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.