Hire an AI customer issue escalation coordinator

Everything it can hand back

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

• What your records already say about the issue, each source named, and the open question
• An escalation brief with impact, what was tried, what you need and by when
• A reply to the customer with the real answer or date, checked so it promises only what was agreed

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

• 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: A customer has written three or more times and the thread has no answer.

• Step 1: What is known. Facts from your docs, tickets and chats with each source named, what was told to the customer, and the open question.
• Step 2: Escalation brief. A brief for the owner with customer impact, what was tried, what you need from them and by when.
• Step 3: Reply draft. A reply to the customer in your voice with the real answer or date, and what to check first.
• Step 4: Checked reply. Each promise marked agreed or removed, tone flags, and a repaired reply. Nothing is sent without your yes.
• Hand-back summary. Each step's file, any step not run and why, and every MISSING line in one list.

How the work is checked

• Each step passed its own checks, or the run stopped at the step that failed and says why.
• The steps ran in order, and each one used the result of the one before.
• Nothing was invented to fill a gap. Every gap is a MISSING: line.
• Nothing was sent, published or paid for without a clear yes.
• 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

• Find what is already known. Reads your docs, tickets and chats, lays out what is known with each source named, and states the open question.
• Write the escalation brief. Writes a brief for the owner with the customer's impact, what was tried, what you need and by when.
• Escalate and wait. A pause. Send the brief to the owner and wait for their answer or a date. Paste it back.
• Draft the customer reply. Drafts the customer reply with the real answer or date, in your voice.
• Check every promise. Checks each promise against what the owner agreed, flags tone, and repairs the reply before you send it.

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 get-a-stuck-customer-issue-unstuck-and-close-the-loop 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/get-a-stuck-customer-issue-unstuck-and-close-the-loop/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 issue and its history: what the customer asked and what was said back
• The customer's own messages, in full
• Who can fix this kind of problem and how to reach them
• Your docs, past tickets or chat logs on the topic (optional)

Helpful context (optional)

• The customer's order and subscription history
• Similar past tickets
• Your refund and goodwill rules

Tools and access

• Any good chat AI: Research, briefs and replies are all text.
• Your help desk and chat tool: Where the past tickets and the owner's answer live.
• 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.
• Any good chat AI: Claude, ChatGPT and Gemini all handle a one-message prompt like this well.

Functions and deliverables

• Customer issue escalation coordinator: Collect the facts of a stuck issue, prepare an owner brief and draft a checked reply from the owner's actual answer.
  • What your records already say about the issue, each source named, and the open question
  • An escalation brief with impact, what was tried, what you need and by when
  • A reply to the customer with the real answer or date, checked so it promises only what was agreed
• 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.
• Escalation brief writer: Turn a stuck support issue and ticket history into an escalation brief with impact and a clear ask.
  • An escalation brief that opens with a clear ask
  • Reproduction steps for bugs
  • An impact summary covering who is hit, how badly and for how long
  • A suggested team to send it to
  • A deadline and next steps
  • Offers to draft a customer update or set a follow-up
  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.
• Customer reply promise checker: Paste the complaint and your draft reply. Get each promise checked, tone flags and a repaired draft.
  • A verdict and a list of unanswered points
  • Every promise marked backed or not
  • A repaired draft
• 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

• A customer has written three or more times and the thread has no answer.
• Support keeps saying "we're looking into it" because nobody inside has said anything.
• An issue needs engineering, the warehouse or a supplier, and the request to them is vague.

Limits to check before starting

• You have one unanswered ticket with no repeat contact: send a normal support reply, or ask a teammate for the answer.
• You only need to check a reply you already wrote: use the Customer reply promise checker.
• You need to write a policy or help page from a fix: write it yourself or ask your AI, then run this only if the customer is still stuck.

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 handoff pack. It's a zip with HANDOFF.md and every skill file this workflow uses.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
• Paste the issue, the customer's messages and who owns the fix. It finds the facts and writes the brief.
• Send the brief to the owner. Wait for an answer or a date and paste it back.
• Read the checked reply and send it. Note the date you promised.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/get-a-stuck-customer-issue-unstuck-and-close-the-loop 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.