Skip to content
Français

Meet Larkfield

Larkfield is the online shop that every course uses as its example. It is made up. On this page, you meet its people, follow its AI work, and see where the data of each course comes from.

Who Larkfield is

A home and garden shop

Larkfield is a Canadian online shop for home and garden products. It also sells its own brand, Larkfield Basics. Marketplace sellers on its website add other categories, such as clothing.

Canada and the EU

Its head office is in Montréal. It sells to customers across Canada and in the European Union. Prices are in Canadian dollars, and customers in the EU pay in euros.

Two languages

Customers write to Larkfield in English and in French. The help desk has bilingual agents. Larkfield built its help-desk software itself.

Online, then shops too

Larkfield sold only online until 2026. That year, it buys a chain of garden centres and a hardware chain. It also has an outlet shop for second-hand items.

A second shop, the bookshop Bramble Books, also uses Larkfield’s help desk.

The people

You meet the same people in many courses. Each person has one role in every course. People in the case studies work at other organisations, even when they have the same first name.

NameRolePronounCourses
GraceHelp-desk lead. She writes the support policy and decides what a good answer is.she
31 courses
AmiraDeveloper. She builds and runs Larkfield’s software.she
31 courses
OmarProduct manager. He asks what a change costs and what it gives the shop.he
36 courses
TomásAI engineer. He often suggests a quick shortcut.he
37 courses
PriyaData scientist. She measures how well a model or an assistant works.she
30 courses
MeiData engineer. She looks after the data, the storage and the data feeds.she
20 courses
KwameSolution architect. Later he owns Larkfield’s AI platform.he
15 courses
CamilleBilingual help-desk agent in Montréal.they
14 courses
SamNew support agent. They ask the questions that a beginner asks.they
13 courses
RuthDirector of customer service.–
NadiaHead of customer operations. She reports to Ruth and chairs the AI governance board.she
LenaPrivacy officer.–
FaridaRisk and compliance lead, the first in that role.she
HanaMerchandising lead. She decides what the shop shows and sells.she
RafaelEmail and customer-relations manager.he
MateoGrowth analyst. He keeps the log of the shop’s tests.he
IvanaCustomer-data steward.she
KenjiStock planner.he
SofiaPayments risk analyst.she
ChloéBilingual support agent.she
MalikTelephony engineer.he
EsmeQA lead. She tests the support assistant before each release.she
HamidReturns warehouse lead.he
InesOutside LarkfieldOwner of Bramble Books, a bookshop that uses Larkfield’s help desk.she
5 courses

Larkfield’s AI work, step by step

The steps follow the learning paths. Each course tells its part of the story in its own time, so this page gives the order of events, not dates.

  1. Find where AI can help

    The help-desk team lists the problems that AI can help with, such as policy questions and sorting tickets. They learn to read the numbers that come with AI.

  2. Learn from the help-desk data

    Mei prepares the ticket data. Priya builds a model that finds the tickets that need a person, and the team puts it into service. A test with deep learning shows that a simpler model is good enough for now.

  3. Use AI across the shop

    Other teams use machine learning too: to find unusual payments, forecast demand, check returned items in photos, route messages, recommend and search products, match customer records after Larkfield buys its shops, test changes with experiments and understand phone calls. Each of these courses stands alone.

  4. Draft replies with a language model

    The team chooses a language model. Amira builds an assistant that drafts replies, and an agent checks and sends each one. The assistant then gets Larkfield’s policy documents, and a workflow that can act, with approvals. Priya measures each change.

  5. Build and protect the platform

    The help-desk software gets a real database, a plan for busy days such as Black Friday, a new screen for agents and sign-in. Bramble Books starts to use the help desk. The team checks the assistant for security risks and connects it to tools.

  6. Run AI in production

    The team tests a fine-tuned model and reads receipts and other documents with AI. It runs releases with checks, plans costs, watches the live workflow and controls all of its AI with a gateway and a registry. Leaders decide go or no go, and a governance board sets the rules.

The data

Each course has its own slice of Larkfield’s data. A course uses only the data that its lessons need, for its own period. So the numbers differ between courses: one course has 1,417 tickets, and another has 300,000. Each number is correct for its course.

Synthetic data is made up for the course. Adapted data is real public data that we changed to fit Larkfield. All the customers in the data are made up.

CourseDataSourcePeriodMain sizesLicence
AI Career Foundations: Roles, Skills and RoadmapsData lessonSmall examples inside the lessons, such as a ten-row ticket tableSyntheticNot given10 tickets in the largest tableNo data files
Essential Mathematics and Statistics for AIData lessonNumbers inside the lessons: test tickets and delivery ordersSyntheticNot givenTest sets of 300 and 1,000 ticketsNo data files
SQL and Data Preparation for AIData lessonThe help-desk exportSyntheticJanuary to June 2026240 customers, 1,417 tickets, 1,874 outcomes
Machine Learning: From Problem to Reliable ModelData lessonThe full ticket export, with the tickets that went to a personSyntheticJuly 2024 to June 2026About 1,000 customers; 16,939 training, 1,179 validation and 1,002 test ticketsNot stated
Deep Learning and Transformers ExplainedData lessonTicket texts with their team, written by a language model from a list of situationsSyntheticNot given5,896 tickets (4,696 / 600 / 600)
Forecasting and Time Series: Predict What Comes NextData lessonDaily demand, orders, tickets, staff rosters, weather and promotionsSynthetic1 April 2024 to 29 March 2026200 products, 403,758 demand rows
Anomaly Detection: Find What Is UnusualData lessonCard payments, refunds, orders, tickets and ticket-API metrics, with planted anomaliesSyntheticPayments: June to November 2025. Orders: April 2024 to March 2026343,074 payments, 24,038 customers
Vision AI: See, Count and InspectData lessonCatalogue photos, photos of returned items, warehouse scenes and customer photosSynthetic and real public dataUntil April 2026733 catalogue photos, 735 return photos; 2,113 files
LLMs: How They Work and How to Choose OneData lessonA small test set of tickets, in English and French, and the support policySyntheticNot given24 tickets; 192 scored repliesNot stated
Building Reliable Applications with LLM APIsData lessonTickets and an orders database, with recorded model answersSyntheticNot given69 tickets; 276 recorded answers
Deploying AI Models for Real UsersData lessonThe tickets of the machine learning course, plus one new monthSyntheticJuly 2024 to July 202618,118 training tickets; 1,400 new tickets in JulyNot stated
Databases and Storage for AI ApplicationsData lessonHelp-desk data in a small size and a large sizeSyntheticSmall: 25 September to 8 October 2026. Large: one year to 8 October 2026Small: 40 customers, 200 tickets. Large: 20,000 customers, 300,000 tickets
RAG: Building AI That Uses Your DataData lessonThe policy collection and Grace’s test questionsSyntheticNot given36 documents, 185 passages, 67 questions
Evaluating and Testing AI SystemsData lessonAn evaluation set, and one simulated month of ticketsSyntheticNot given271 cases (102 / 98 / 71); 1,270 simulated tickets
Testing AI Applications: Manual and AI-Assisted QAData lessonA practice help-desk app with test data, and recorded model repliesSyntheticNot given4 customers, 8 orders, 8 reviews; 300 recorded replies
AI Agents and Workflow OrchestrationData lessonWorkflow tasks, a practice database and policy passagesSyntheticNot given70 tasks, 24 policy passages
AI-Assisted Software DevelopmentData lessonA ticket file and a web-form export in a small code projectSyntheticNot given15 ticketsNot stated
Frontend Architecture and Performance for AI AppsData lessonA mock ticket API, with replayed AI draftsSyntheticNot given10,000 tickets; 69 recorded drafts
Authentication, Permissions and Multi-Tenant ApplicationsData lessonThe help-desk data of the databases course, plus a second shop, Bramble BooksSynthetic25 September to 8 October 2026Larkfield: 40 customers, 200 tickets. Bramble Books: 12 customers, 40 tickets
AI Security, Privacy and Responsible DesignData lessonA practice support assistant: database, documents and web pages, with planned attacksSyntheticNot given26 normal tasks, 42 attacks, 31 passages
MCP: Connect AI Applications to Tools and DataData lessonTickets and policy documents of two shops on one help deskSyntheticNot given21 tickets, 14 documents
Scaling APIs and AI WorkloadsData lessonThe large help-desk data of the databases course, with recorded provider timingsSynthetic9 October 2025 to 8 October 2026300,000 tickets, 20,000 customers
MLOps and LLMOps: Operating AI in ProductionData lessonThe evaluation course’s tickets, recorded model calls and saved service dataSyntheticNot given271 tickets; 1,358 recorded calls; a practice week of 5,754 tickets
Fine-Tuning and Adapting AI ModelsData lessonThe deep learning course’s training tickets, with new labelsSyntheticNot given4,696 tickets; 900 in the training sample
Document and Multimodal AIData lessonA document set: till receipts, policies, a price list and problem filesSyntheticReceipts from June to September 202665 documents, 53 of them receipts
AI System Design and Cost EngineeringData lessonThe RAG course’s documents and questions, a demand file and measured costsSyntheticNot given36 documents, 67 questions, 659 recorded calls
Governing AI Agents: Gateways, Registries and ControlsData lessonA provider simulator: recorded answers from earlier courses and a simulated billSyntheticOne month: September 20265,253 recorded answers; 40,754 model calls
Observability for AI Agents: Traces, Costs and Audit TrailsData lessonOne saved week of the support workflow: simulated traffic and replayed decisionsSynthetic12 to 18 October 2026316 runs, 1,331 audit records
Leading AI Products and TeamsData lessonAn evidence pack, with numbers from the evaluation, operations and document coursesSyntheticNot given271 tickets; 199 judged drafts
AI Governance: Policies, Risk and AccountabilityData lessonThe AI portfolio, the policy and the governance board’s filesSyntheticNot given8 AI systems
Portfolio Capstone: Build, Evaluate and Ship an AI ProductData lessonThe RAG course’s documents, plus Bramble Books’ documents and a question bankSyntheticNot given36 + 15 documents; 103 questions
Text Classification and Routing: Send Each Message to the Right PlaceData lessonThe support inbox, in English and FrenchSyntheticSeptember 2025 to January 202610,000 messages (7,071 English, 2,929 French)
Recommendation and Personalisation: Show Each Person What MattersData lessonThe shop log: views, basket adds and ordersSynthetic1 February 2025 to 5 July 20262,994 products, 40,000 customers, 805,316 events
Search and Ranking: Find the Best MatchData lessonThe catalogue, test queries and judgments from a real public dataset (WANDS); prices, stock and the query log are made upAdapted from real public dataQuery log: 1 September to 26 October 202540,066 products, 624 queries, 20,000 searches
Entity Resolution and Record Matching: Is This the Same Thing?Data lessonCustomer lists of the shop, the loyalty programme and the garden centres, and two supplier feedsSyntheticNot given60,108 records of 37,500 people; supplier feeds of 4,460 and 3,501 products
Experiments and Causal Impact: Did Our Change Work?Data lessonA simulator of the shop, its customers and their ordersSyntheticJune 2024 to November 202540,000 to 93,463 customers in each scenario
Speech AI: Transcribe, Understand and SpeakData lessonPhone calls to the help desk, made with open text-to-speech voicesSyntheticNot given340 calls (260 for learners: 175 English, 85 French)

These courses use a simple help desk and do not name Larkfield: Python for Practical AI Engineering; Git and Team Development Essentials; Build and Deploy Your First API; Docker and Cloud Essentials for AI Developers; CI/CD, Testing and Safe Releases.

Is Larkfield real?

No. Larkfield, its people and its customers are made up. A real company or person with the same name is a coincidence.

Why one shared company helps you

  • You learn the business once. Each new course starts with a problem that you already know.
  • You see how the parts connect: the model of one course becomes the data, the cost or the risk of a later course.
  • The decisions feel real: costs, customers, rules, and people who do not agree.
  • No real customer’s data is used, so we can show you all of it.