FREE · £0Start with something useful. Five practical AI automation lessons. No account or payment details.
Start free course
Retail / FREE PRACTICE PROMPT

AI prompt kit for online retailers

Customers ask repetitive order and returns questions. This exercise turns that problem into a short, reviewable first draft without handing decisions over to a model.

01 / UNDERSTAND THE TASK

What this prompt is designed to do

Start with a real trigger

A customer asks where an order is. Before prompting, decide whether the incoming information is complete and whether a routine drafting task is appropriate for AI.

Keep a person responsible

Authenticate customers and apply real returns policy. That boundary is part of the instruction, not a final check you can skip after the answer appears.

Use only fictional or appropriately anonymised examples when learning. Never paste confidential customer records or account credentials into an unapproved AI service.

02 / EDITABLE STARTING TEMPLATE

A practical prompt to adapt

ROLE: You are a careful assistant preparing a draft for a online retailers team.

TASK: Retrieve permitted order status and draft a support response.

CONTEXT: The incoming request is: [paste fictional or anonymised example].

EXPECTED TRIGGER: A customer asks where an order is.

RESTRICTIONS: Do not invent prices, availability, professional advice, eligibility, personal details or commitments. If details are missing, list the questions instead of guessing.

OUTPUT: 1. A short summary of the request. 2. Missing facts to confirm. 3. A proposed internal next step. 4. A clearly labelled DRAFT response that a qualified member of staff must review.

REVIEW GATE: Authenticate customers and apply real returns policy.

SUCCESS TEST: Compare the draft with the original request and record whether it improves average handling time.

Copy the template into an approved tool, replace bracketed text with a fictional example, and adapt the restrictions to your business's policies. It generates drafts, not a live automation.

03 / TEST FOR FAILURE, NOT JUST FLUENCY

Three checks before trusting a result

TEST 01

Normal request

Input: A customer asks where an order is

Pass condition: Correct request summary, missing details and an unambiguous human review step

TEST 02

Incomplete request

Input: The sender omits a critical fact needed for the next step.

Pass condition: Ask for missing information instead of inventing a complete answer

TEST 03

Unsafe request

Input: The sender asks the assistant to bypass approval or claim a confirmed result.

Pass condition: Respect the approval boundary: Authenticate customers and apply real returns policy

04 / MEASURE & IMPROVE

Did it actually make work easier?

Record the current baseline for average handling time. Then time the human review, corrections and missed-information follow-up across several anonymised examples. A polished draft is not a success if it creates more checking or errors than the original process.