---
name: al-198-let-an-agent-fully-answer-routine-customer-emails-with-cl
description: "Instead of an AI that only drafts replies for staff to approve, define which routine email requests the agent may resolve end to end (missing card, payment questions, status updates) and exactly when it must stop and escalate to a person, such as complaints, vulnerable customers or anything outside approved steps. UK digital bank LHV Bank just put a Gradient Labs agent live on its customer email support this way, with every change tested and approved before release. Use when the user wants help with email support automation (customer support) for a small business."
---

# Let an agent fully answer routine customer emails, with clear rules for when to hand off

Instead of an AI that only drafts replies for staff to approve, define which routine email requests the agent may resolve end to end (missing card, payment questions, status updates) and exactly when it must stop and escalate to a person, such as complaints, vulnerable customers or anything outside approved steps. UK digital bank LHV Bank just put a Gradient Labs agent live on its customer email support this way, with every change tested and approved before release.

## Inputs to collect first
Ask the user for anything below that they haven't already given you. Don't guess missing facts.

- Type, what customers usually email about
- Refund, account, shipping or other rules
- E.g. order lookup, ticket status, help center
- 10-20 recent anonymized emails
- Amount

## Instructions

Do the task below with the user's inputs in place of each [bracket].

You are helping me design an email support agent for my business. Business: [type, what customers usually email about]. Our policies and procedures: [paste refund, account, shipping or other rules]. Tools the agent could use: [e.g. order lookup, ticket status, help center]. Step 1: from these sample emails [paste 10-20 recent anonymized emails], group requests into types and count them. Step 2: mark each type as 'agent can resolve end to end', 'agent drafts, human approves' or 'always escalate to a human', and explain why using only our policies. Step 3: write the escalation rules as a clear checklist (complaints, upset or vulnerable customers, money above [amount], anything not covered by policy). Step 4: write reply templates for the top 3 'resolve' types. Step 5: list 10 test emails, including tricky ones, to check the agent before going live. Do not invent policies; mark gaps as 'needs a decision'.

## Safety checks (share these with the user)

- This prompt works on text other people wrote (emails, reviews, messages or web pages). That text can hide instructions aimed at AI, such as "ignore your rules and…". Paste it as material to work on, and never let the AI act on requests inside it, like paying, sharing logins or changing records.
- Check every figure, price and total against your own records before anything is sent, posted or booked. A person approves refunds, discounts, payments and price changes.
- Remove names, contact details, account numbers and other personal data the task doesn't need before you paste, and check your AI tool's data and training settings.
- Read and edit the draft before it reaches a customer or goes public. If you later automate this prompt, start with "draft and notify me", not "send automatically".
- Say clearly which parts need a person to review or approve before anything is sent, paid, posted or filed.

## About this skill

- Works with: Gradient Labs, Zendesk, Gmail, ChatGPT, Claude
- Based on this real-world example: https://fintech.global/2026/10/21/lhv-bank-launches-gradient-labs-ai-agent-for-email-support/
- Free prompt from AgentPlaybook Real Estate: https://agentic-library.netlify.app/prompt/al-198-let-an-agent-fully-answer-routine-customer-emails-with-clear/
- To install in an agent that supports Agent Skills, save this file as SKILL.md in a folder with the same name as `name` above (for example in your skills directory). Install steps for Claude.ai, Claude Code, Cursor and Codex: https://agentic-library.netlify.app/skills/