Hire an AI support handoff planner

Everything it can hand back

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

• An escalation procedure: triggers, evidence, receiving role, acceptance, fallback and closure
• A list of gaps, such as roles with no owner or promises with no deadline
• Draft updates for your team and for customers
• A summary and one next step

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

• Inventing facts, figures, dates, quotes or completed actions.
• Passing on an earlier step's output without checking what it says.
• Hiding a failed check to finish the run.
• 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 waited three days because two teams each thought the other had the case.

• step-01-process-and-sop-writer.md. The escalation procedure: triggers, evidence, receiving role, acceptance, fallback and closure, with gaps shown.
• step-02-stakeholder-update-writer.md. Update drafts for your team and for customers, with confirmed facts kept apart from estimates.
• step-03-hand-back-summary.md. Files saved, deadlines still blank, checks not run and one next step.

How the work is checked

• Response and resolution commitments stay distinct. No unsupported deadline or escalation authority is invented.
• If real cases were given, walk at least one through the procedure and say where it would have moved sooner.
• Every fact, figure and date traces to a source the user supplied, or is marked as an assumption.
• Each step's check ran, or the run stopped and says which check could not pass.
• 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

• Process and SOP writer. Writes the escalation steps from your approved process, with owners and gaps. Hands step 2 the triggers, roles and promises so the messages quote them.
• Stakeholder update writer. Drafts team and customer updates from the procedure and your real promises. Hands back messages that keep confirmed facts apart from estimates.

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 define-a-customer-support-escalation-agreement 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/define-a-customer-support-escalation-agreement/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 support tiers and who sits in each (from your help desk or org chart)
• Service promises already made, such as reply times (from contracts or your help page)
• Who owns which kind of issue
• The channels you support, such as email, chat or phone
• Two or three real cases that got stuck, with customer names removed (optional)
• Your rules on what you tell customers (optional)

Helpful context (optional)

• Your help desk's list of ticket categories
• Past customer emails about delays, with names removed
• Your on-call or rota schedule
• Any service terms you sent to customers

Tools and access

• Any good chat AI that reads files, such as Claude, ChatGPT or Gemini: It needs your tiers, promises and cases in one run.
• Any good chat AI: It only needs your notes pasted in. A tracker connection is a bonus, not a need.

Functions and deliverables

• Support handoff planner: Set support handoff rules and owners. Draft customer updates from approved promises, keeping first-reply targets separate from fix deadlines.
  • An escalation procedure: triggers, evidence, receiving role, acceptance, fallback and closure
  • A list of gaps, such as roles with no owner or promises with no deadline
  • Draft updates for your team and for customers
  • A summary and one next step
• Process and SOP writer: Turn how your team works into a clear SOP. Give it a process name or old notes. You get a RACI table, a flow, steps and exceptions.
  • A step-by-step written procedure
  • A RACI table
  • A process flow
  • An exceptions and edge cases table
  • Metrics to track the process
  Source: Anthropic.
• Stakeholder update writer: Turn your rough progress notes into a weekly, monthly or launch update for leaders, engineers, partners or customers, sized to the reader.
  • A draft update sized to your reader, ready to paste
  • A status colour with a one-line reason
  • Each risk with a plan or an owner
  • Each decision with options and a recommendation
  • A list of facts you still need to add
  • A version for a second reader (optional)
  Source: Anthropic.
• Support desk automation builder: Build your own support desk automation. Give it your help desk and billing tools. You get scripts, reply templates and a triage routine that drafts replies.
  • Integration scripts
  • A config file
  • Reply templates with variables
  • A triage workflow that drafts for approval
  • A reusable skill definition
  Source: nbashaw.
• 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 waited three days because two teams each thought the other had the case.
• You are adding a second support tier and need the handoff written down.
• A big client asks what happens if their case is not fixed in time.
• A new support lead asks 'who do I escalate to?' and gets four answers.

Limits to check before starting

• You need to answer one upset customer now. Use the Angry customer reply writer.
• You are in the middle of an outage. Use Service outage update writer.
• You want to clear a backlog of tickets. Use Support reply and help-page writer.
• You want legal service levels for a contract. A lawyer must agree those. This writes your internal process.

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 workflow pack and add it to Claude, ChatGPT or Gemini.
• Paste your tiers, promises and ownership rules. Add the stuck cases if you have them.
• Say: follow the workflow file, keep unknown deadlines blank and stop if a check fails.
• Read the gap list first. Fill each blank with a real decision from your team.
• Walk one stuck case through the procedure to see if it would have moved faster.
• Share the final procedure with each tier lead before anyone uses it.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/define-a-customer-support-escalation-agreement 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.