Skip to content
Français

Courses

42 courses, from your first steps in Python to AI systems in production. Every course names what you need before you start, so you can begin at the right place.

Showing all 42 courses.

Available now

Career

AI Career Foundations: Roles, Skills and Roadmaps

See what people in AI really do, find your starting point, including the experience you already have, and make a realistic plan to get there.

Course · 18 lessons · 4–6 hr

Foundations

Python for Practical AI Engineering

Write, run and debug small Python programs, and organise them as a project that someone else can set up and use.

Course · 18 lessons · 18–24 hr

Foundations

Essential Mathematics and Statistics for AI

The mathematics and statistics behind AI, shown with real examples and charts you can change. You learn what the numbers mean and how to use them in decisions, not how to calculate by hand.

Course · 18 lessons · 12–16 hr

Data and machine learning

SQL and Data Preparation for AI

Get the data for an AI project out of a database, clean it, and prepare it for a model without leaking the answer. You write real SQL in the browser from the first lesson.

Course · 18 lessons · 12–16 hr

Data and machine learning

Machine Learning: From Problem to Reliable Model

Train a model that you can trust, from the business question to a handoff that another person can run. You build a ticket escalation classifier step by step, and test it honestly at every step.

Course · 27 lessons · 26–32 hr

Data and machine learning

Deep Learning and Transformers Explained

See how a neural network learns, from one neuron to a small transformer. You train a network that routes Larkfield's support tickets, find out why its training goes wrong and fix it, and then open a real pretrained language model to see what is inside.

Course · 23 lessons · 28–36 hr

LLM applications

LLMs: How They Work and How to Choose One

Learn what a large language model really does, from tokens to post-training, what it can and cannot do, and how to choose one for your own task with evidence instead of a leaderboard.

Course · 16 lessons · 8–12 hr

LLM applications

Building Reliable Applications with LLM APIs

Build an application that uses a language model and stays reliable when the model is wrong, slow or unavailable. You build Larkfield's ticket assistant step by step, from one request to validated answers, safe tools and tested failure paths.

Course · 19 lessons · 22–30 hr

LLM applications

RAG: Building AI That Uses Your Data

Build an assistant that answers from your own documents and shows where every answer comes from. You turn Larkfield's policy documents into a searchable knowledge base, measure what retrieval finds and misses, and make the assistant say "the documents do not say" when they do not.

Course · 18 lessons · 24–32 hr

LLM applications

AI Agents and Workflow Orchestration

Build a system that resolves support tickets step by step, and stays safe while it does. You turn Larkfield's help desk work into a workflow that looks up evidence, proposes an action, waits for a person's approval before any change, and records what happened.

Course · 18 lessons · 22–30 hr

LLM applications

Evaluating and Testing AI Systems

Find out whether a new version of an AI system is really better, and whether it broke anything that matters. You build an evaluation harness for Larkfield's support assistant, with a versioned set of tickets, scores you can trace, human and model judges you have checked, and a release decision you can defend.

Course · 19 lessons · 20–26 hr

Data and machine learning

Fine-Tuning and Adapting AI Models

Decide with evidence whether to fine-tune a model, and if you do, do it so that you can trust and maintain the result. You prepare clean training data, train a small LoRA adapter on an ordinary computer, compare it with the prompt-only system on the same held-out tickets, and decide whether it ships.

Course · 12 lessons · 10–14 hr

LLM applications

Document and Multimodal AI

Read receipts, scans, photos, tables and policy documents with code and AI, and show exactly where every value came from. You build Larkfield's document pipeline, compare the PDF text layer, OCR and a vision model on the same pages, and send only the uncertain values to a person.

Course · 19 lessons · 16–22 hr

Engineering and deployment

Git and Team Development Essentials

Track your work with Git, work with a team through branches and pull requests, and recover from common mistakes.

Course · 15 lessons · 5–7 hr

Engineering and deployment

AI-Assisted Software Development

Use a coding assistant without losing control of your code. You give it a bounded task with clear evidence of done, read every line it changes, check the packages it suggests, and debug with tests instead of blind rewrites, on your own ticket-cleaner from the Python course.

Course · 15 lessons · 10–13 hr

Engineering and deployment

Build and Deploy Your First API

Build a small web API with FastAPI, document it with OpenAPI and Swagger UI, test it with Postman and pytest, and deploy it.

Course · 21 lessons · 11–15 hr

Engineering and deployment

Deploying AI Models for Real Users

Serve the model that you trained in Machine Learning to real users. Package it with its contract, choose batch, online or asynchronous serving, build and measure the prediction service, and release a new version with a tested way back.

Course · 15 lessons · 8–12 hr

Engineering and deployment

Docker and Cloud Essentials for AI Developers

Package the ticket API in a container image, run it with a database on your computer, and deploy it to Azure Container Apps with its settings outside the image, a cost check and a full clean-up.

Course · 15 lessons · 7–10 hr

Engineering and deployment

CI/CD, Testing and Safe Releases

Build a pipeline that checks every change, builds one image, and promotes it to staging and production with an approval. Then release an AI model change safely, migrate a database without downtime, roll back and ship a hotfix.

Course · 15 lessons · 8–12 hr

Engineering and deployment

Databases and Storage for AI Applications

Give an AI application a real storage design. You turn Larkfield's ticket API into a service that owns its data in PostgreSQL, keeps files in object storage and vectors next to the records, stays fast on large data, and can be restored after a mistake.

Course · 16 lessons · 16–22 hr

Engineering and deployment

Scaling APIs and AI Workloads

Get an AI service ready for ten times the usual traffic, with proof. You measure Larkfield's ticket API first, then add concurrency, a safe cache, a job queue with workers, and limits that keep overload under control, and you show every change with a load test.

Course · 19 lessons · 17–23 hr

Engineering and deployment

Frontend Architecture and Performance for AI Apps

Build a fast, clear and safe screen for AI work. You turn Larkfield's ticket API into a real help-desk interface with React and TypeScript, show AI drafts as they are written, track slow AI jobs, and prove every speed-up with a measurement in the browser.

Course · 19 lessons · 20–26 hr

Engineering and deployment

Authentication, Permissions and Multi-Tenant Applications

Make one API safe for two organizations. You add sign-in, roles and organization boundaries to Larkfield's ticket API, so that every request answers three questions on the server — who is calling, what may they do, and in which organization — and you prove it with tests that try to break it.

Course · 19 lessons · 16–22 hr

Engineering and deployment

AI Security, Privacy and Responsible Design

Find out how an AI assistant can be tricked, and make sure a tricked assistant still cannot do harm. You list the risks of Larkfield's support assistant, attack it with harmless injections and fix the consequences in code. Then you map its personal data, design human review, and finish with a security test set and an incident plan.

Course · 18 lessons · 18–24 hr

Engineering and deployment

MLOps and LLMOps: Operating AI in Production

Keep an AI service working for its users after it goes live. You make Larkfield's ticket service operable one module at a time, with owners, objectives, versions, telemetry, monitoring, safe releases and runbooks, and you catch a bad release before customers tell you.

Course · 19 lessons · 16–22 hr

Engineering and deployment

AI System Design and Cost Engineering

Design an AI product before you build it, and know what it will cost. You write Larkfield's design and cost proposal for a document assistant that several shops share, one module at a time. Every number in it is measured, a published price or a stated assumption.

Course · 19 lessons · 16–22 hr

Career

Portfolio Capstone: Build, Evaluate and Ship an AI Product

Build, evaluate and ship your own AI product, with the evidence to show it works. You watch a complete document assistant for two shops being built step by step, and you build your own beside it, one lesson at a time.

Course · 22 lessons · 30–45 hr

LLM applications

MCP: Connect AI Applications to Tools and Data

Connect an AI application to tools and data once, with a standard protocol, and keep control of what it may do. You build one MCP server for Larkfield's support knowledge, inspect it, connect an AI application to it, and protect it with sign-in, permissions and a person's approval.

Course · 22 lessons · 16–21 hr

Leadership and governance

Leading AI Products and Teams

Lead AI work that you do not build yourself. You make the decisions that Larkfield's leaders really faced, from evidence that the technical courses recorded, and you finish with an AI product and team plan for your own field.

Course · 22 lessons · 12–16 hr

LLM applications

Testing AI Applications: Manual and AI-Assisted QA

Find, reproduce, report and prevent the failures of AI features. You test a practice version of Larkfield's support assistant with planted bugs, write bug reports that people and coding agents can act on, and finish with a regression set and a release decision.

Course · 24 lessons · 22–28 hr

Engineering and deployment

Observability for AI Agents: Traces, Costs and Audit Trails

See what your AI agents do, what they cost and who approved each change. Instrument a live support workflow with OpenTelemetry, find agent failures in traces, split cost by model and step, and keep an audit trail that answers "why did the agent do this?".

Course · 28 lessons · 26–32 hr

Engineering and deployment

Governing AI Agents: Gateways, Registries and Controls

Put every AI agent in your organisation behind controls that code enforces. Apps ask for a capability instead of a model, every agent is registered with its own identity, and one model gateway and one tool gateway check, limit and record every call.

Course · 21 lessons · 24–30 hr

Leadership and governance

AI Governance: Policies, Risk and Accountability

Set the rules for AI in an organisation, give every AI system an owner, and prove that the rules are followed. You govern Larkfield's AI portfolio, read the main laws and standards in plain words, and finish with a governance pack for the next year.

Course · 19 lessons · 15–20 hr

Applied AI

Anomaly Detection: Find What Is Unusual

Find the few events that matter among millions that do not. Compare rules, robust statistics, control charts, isolation, time-series and deep methods on the same data, choose by the cost of a miss, and run the detector as a daily job that people trust.

Course · 38 lessons · 30–36 hr

Applied AI

Forecasting and Time Series: Predict What Comes Next

Predict demand, tickets and staff needs well enough to act on them. Compare simple, statistical, machine learning and foundation-model forecasts in one honest backtest, turn the forecast range into a stock order and a staff roster, and run it as a weekly job.

Course · 27 lessons · 26–32 hr

Applied AI

Text Classification and Routing: Send Each Message to the Right Place

Send every support message to the right team, with a priority, in English and French. Compare rules, classical models, embeddings, a fine-tuned encoder, zero-shot models and LLMs on one test set and one cost table, send the unsure messages to a person, and run the router as a small service.

Course · 37 lessons · 30–36 hr

Applied AI

Recommendation and Personalisation: Show Each Person What Matters

Show each customer the products that matter to them. Split the shop log by time, beat a strong popularity baseline, compare neighbours, matrix factorisation, content and a two-stage ranker on the same customers, and run the winner with business rules, a fallback and privacy controls.

Course · 29 lessons · 28–34 hr

Applied AI

Search and Ranking: Find the Best Match

Make search find the best product first. Measure relevance with graded judgments, then compare BM25, query understanding, dense and hybrid retrieval, re-ranking and learning to rank on the same queries, and choose a design by relevance, speed and cost.

Course · 30 lessons · 26–32 hr

Applied AI

Entity Resolution and Record Matching: Is This the Same Thing?

Decide when two records describe the same customer or product. Clean and block the records, then compare rules, string measures, probabilistic linkage, pair classifiers, embeddings and a language model for the unsure pairs on the same data, and turn pairs into entities that people can review and undo.

Course · 29 lessons · 22–28 hr

Applied AI

Experiments and Causal Impact: Did Our Change Work?

Find out whether a change really worked. Design and analyse A/B tests, avoid the traps of peeking and many metrics, estimate effects when you cannot run a test, find who benefits with uplift models, and check every answer against a simulator that knows the truth.

Course · 30 lessons · 26–32 hr

Applied AI

Speech AI: Transcribe, Understand and Speak

Turn phone calls into text and decisions, and build a phone line that answers by itself. Measure speech recognition honestly on phone-quality audio, compare voice detectors, recognisers, speaker splitting and voices on the same calls, build a small IVR that understands speech and keypad tones, and compare it with a voice agent.

Course · 36 lessons · 32–38 hr

Applied AI

Vision AI: See, Count and Inspect

Turn photos into decisions you can defend. Sort product photos, count boxes on a pallet, find damage on returned items and match a customer's photo to the catalogue. Compare simple rules, pretrained models, embeddings, detectors and vision-language models on the same images, choose by the cost of a mistake, and run the chosen model as a small image service.

Course · 30 lessons · 28–34 hr

Coming later

We publish each course when beginners have tested it. Hours are estimates and include practice.