Skip to content
Faisal Mahmud TusherDigital marketing, SEO & analytics
with Faisal Tusher

AI in Marketing › Expert

Capstone: An AI Production Plan for a Children's Shoe Retailer

The closing project of the expert AI in marketing level. You plan a year of AI in production for an invented children's shoe retailer whose AI-written queries and tags reached its reports unchecked, whose support team wants an assistant and reply drafts, and whose agency wants three platform settings handed to automation before its busiest season. The plan gates every piece of AI-written technical work, launches and tests the assistant behind its checklist, splits saved replies from drafts and tests each automation proposal on its own measure, with an owner, a calendar slot outside the season and the reading that will judge each part.
Capstone projectExpert levelModule 3: Proving what platform automation adds7 minUpdated

Brief

Dynourkin Shoes is an invented online retailer of children's shoes with an online fitting guide and staffed chat. Much of its year is taken in the weeks before the school term starts, when parents buy in a hurry and exchange sizes just as fast.

The analyst writes queries by pasting customer rows into a personal AI account. A generated tag for the fitting guide went live last month without a preview, and nobody can say which of the revenue figures in the board pack came from generated SQL. Support wants an assistant to answer sizing and delivery questions in chat and drafts for its agents. The agency wants broad match, broad audiences and an add-to-cart optimisation event, citing the platforms' own reports, and wants all three live before the season.

This plan runs AI in production for a year inside the operating model from the advanced AI in marketing level: what ships, what is tested, in what order and how each result is read.

Inputs and constraints

Illustrative example — not a real result

Dynourkin Shoes: the team, the year and the AI use register

Team: the owner; a marketing manager; an analyst 3 days a week; a customer service lead with 4 agents, 7 in season; a fitting specialist who owns the fitting guide; an operations manager who owns delivery, returns and exchanges; a freelance developer with publish rights on the tag container; a paid media agency.

Year: the back-to-school season runs from mid-July to the second week of September and carries 41% of annual revenue; a spring sale runs for 2 weeks in April; returns and exchanges are accepted within 30 days.

Register rowToolOwnerWhat the row shows
Revenue and channel queriesThe analyst's personal AI accountNone recordedRows pasted with parents' names, postcodes and children's foot measurements
Fitting guide tagAn approved assistant; published without previewNone recordedLive for 5 weeks
Product page markupAn approved assistant, written page by page for the 60 best sellersNone recordedA review rating on 22 pages that show no reviews
Board pack revenueUnknownNone recorded2 of last quarter's 3 monthly figures differ from the shop platform's report, by 9% and 14%

Tracking plan row: fitting_guide_complete, with size_result and fit_width, sent once when the guide's result shows. The live tag sends fitting_complete on each of the guide's 4 steps, with a parent_email parameter taken from the "save my child's size" form.

Illustrative example — not a real result

Dynourkin Shoes: contact reasons and the help centre

Contact reasonA month out of seasonA month in seasonContent behind the answerOwner
Which size for my child5202,100Fitting guide and size chartsFitting specialist
Will these fit wide or narrow feet180640Wide-fit article, 2 versions liveNone named
Will it arrive before term starts901,300Delivery policyOperations manager
Where is my order3001,500Read-only order lookupOperations manager
Exchange for another size2601,200Exchange policyOperations manager
Faulty shoes60150Guarantee termsCustomer service lead
Complaints40210NoneCustomer service lead
  • Product-page and fitting guide chat: about 3,000 visitors open it a month out of season; 26% order within 30 days; contribution after returns and exchanges averages £14 an order.
  • Agents' target is chats closed per hour. The saved reply library holds 38 replies, 12 with no owner.
Illustrative example — not a real result

Dynourkin Shoes: the ad accounts and the agency's proposals

CampaignSet-upA month out of season
Google Ads, core searchExact and phrase; Smart Bidding, target cost per conversion £9900 conversions; most within a day of the click, some up to 2 weeks later
Google Ads, brandBrand keywords1,400 conversions
Meta, prospectingInterests in parenting and school preparation; purchase optimisation; customers excluded520 purchases reported, 450 matched to shop orders
Meta, wide-fit range3 ad sets sharing the budget; purchase optimisation; learning limited30 purchases, 260 adds to cart

The agency's proposals: core search to broad match; prospecting to Advantage+ audience; the wide-fit campaign to add-to-cart optimisation. All three to go live in the first week of July.

Constraints you must work within:

  • Nothing is launched, changed or tested in the back-to-school season, and every test is read before the season starts.
  • Customer records go only into tools the data protection lead has approved. Any data rule in the plan is a starting point for that lead to confirm, and nothing in it is legal advice.
  • The shop platform is the record of orders and revenue; platform-reported figures are not.
  • The assistant says it is automated, and a person is one request away throughout every conversation.

Task

  1. Gate AI-written technical work. Write the gate every query, tag and piece of markup passes before it ships, built on the AI-written code review checklist, so whatever a Language Model writes is proved against something independent before it reaches a report. Then apply the gate to what is already live: the analyst's practice is stopped and handled under the AI use policy; each board pack figure is rerun and reconciled as the routine for checking AI-written SQL sets out; the fitting guide tag is rebuilt to its plan row and previewed under both consent choices following the tracking code routine; and the markup becomes a mapping from template fields with every rating removed where reviews do not show. Give each use its row, owner and tier in the AI use register.
  2. Scope and gate the assistant. Place every contact reason by risk, keep complaints and customers who may be vulnerable with people, and design the handover and the disclosure before choosing what the assistant answers. Fix the wide-fit article and the unowned replies first. The AI customer service launch checklist is passed before any customer sees the assistant.
  3. Split saved replies and drafts. Use the saved replies and AI drafts comparison to split the delivery promise, the exchange policy and fitting questions between an owned Saved Reply and drafts, naming each owner, and replace the chats-per-hour target before drafts arrive.
  4. Design the assistant test. Write the plan in the experiment hypothesis template from the AI chat assistant test: its primary metric, each Guardrail Metric with its limit, the margin and the decision rule written before launch, and the reading after the exchange window.
  5. Plan the automation tests. Write one plan per proposal on the measure its page sets: the broad match expansion test under the Smart Bidding target, the audience targeting breadth test and the optimisation event test, the wide-fit ad sets consolidated first. The guide to AI in ad platforms is why the platforms' own reports decide none of them.
  6. Build the calendar. Order the gate, the launch, the drafts, the chat test and the three platform tests so each result is read alone and none falls in the season. Record each decision, with its check date and what would reverse it, in the marketing decision log.
  7. Write the plan. One document with a page per part, naming its owner, calendar slot and reading, with the working behind it appended.

Evaluation criteria

CriterionWhat a strong answer showsCommon gap
AI-written technical workRequires a written definition before any request, field names and invented rows in an approved tool, reading and testing against an independent total, release through the usual rules and the verified version saved with its promptGenerated work trusted because it runs
Assistant scope and launchSorts every contact reason by risk, keeps complaints and customers who may be vulnerable with people, designs handover and disclosure first and passes the launch gate before any customer sees the assistantScope chosen by volume and the handover designed last
Drafts and saved repliesGives policy answers to owned saved replies and varied product questions to drafts from complete content, lets drafts draw on the library and leaves commitments to agentsOne method for every question
The assistant testJudges assistant-first chat on contribution per chat visitor, net of returns and the cost of answering, with accuracy, handover and repeat-contact guardrails and a rule written before launchDeflection reported as the result
Platform automation testsTests one change at a time, judged on the measure each test page sets, with purchases reconciled to the shop's orders where the page says so, sets learning periods aside, waits for conversion delay and writes each decision rule before launchThe platforms' own reports taken as proof
A calendar that can be readPuts the launch, the chat test and the platform tests in an order where each result stands alone and nothing lands inside the back-to-school seasonEverything switched on at once just before the season

A strong submission also says what the agency hears about its July date and why, and which of last month's problems the gate would have stopped, at which line.

Submission checklist

0/7

Pages this lesson applies

Templates and checklists used

Terms used on this page

Also related

Related