Course Taxonomy: Data & AI

AI Engineering: Build and Ship Production-Ready AI Systems

Part 1: Foundations

Start from zero. Build the vocabulary and mental models everything else depends on.

  • Module 1: What AI actually is, minus the hype: AI vs ML vs deep learning. Models, parameters, weights, training vs inference. Supervised, unsupervised, reinforcement learning. Where AI is already running inside your company, whether you approved it or not.
  • Module 2: Neural networks and transformers: Neurons and layers for engineers, not mathematicians. Why transformers replaced everything before them. Attention, explained so it clicks. Training vs running a model, and why the cost profiles differ wildly.
  • Module 3: Inside a large language model: Tokenization, and why it explains half the weird behavior you have seen. Embeddings. Context windows and the constraints they put on your design. Temperature and sampling: the dials you will actually turn. Why models hallucinate, and what that means for what you are allowed to build.

By the end of Part 1 you can read any AI claim, vendor pitch, or job posting and know exactly what is being said, and predict where a model will fail before you write code.

Part 2: Building with LLMs

Go from understanding models to building things with them that hold up under real use.

  • Module 4: Prompt engineering that survives contact with users: Zero-shot vs few-shot. System vs user prompts, and who controls what. Structured outputs your code can trust. Chain of thought. Common failure patterns. Prompt injection: your first look at the attack surface.
  • Module 5: Embeddings and vector search: What an embedding represents. Similarity search. Choosing a vector database without regret. Chunking strategies, which is where most real systems quietly go wrong.
  • Module 6: Retrieval augmented generation (RAG): The most requested AI capability in the enterprise today. The architecture end to end. RAG vs fine-tuning, and making that call correctly the first time. Evaluating retrieval quality, because “it seems better” is not an answer. The pitfalls that sink most first builds.
  • Module 7: Function calling and tool use: The hinge the rest of the course turns on. How function calling works. Designing tool schemas a model will use correctly. Handling errors, retries, and partial failure.

By the end of Part 2 you have built a grounded RAG system over real data and connected a model to working APIs.

Part 3: Agents and MCP

How models plan, take multi-step actions, and connect to real systems.

  • Module 8: AI agents: The agent loop. The ReAct pattern. Planning and reflection. Where agents fail in production, drawn from real failures rather than demos. How to avoid betting on the wrong framework.
  • Module 9: Model Context Protocol (MCP): The piece almost nobody has hands-on experience with yet, which is exactly why it is worth having. What problem MCP solves. Client and server architecture. Tools, resources, and prompts. Connecting to a live MCP server, then building your own. Security considerations, which are not optional.
  • Module 10: Multi-agent systems: Single agent vs multi-agent, including the honest case for staying with one. Sharing context and state. Orchestration patterns. Guardrails against runaway loops and runaway bills.

By the end of Part 3 you have built and connected an MCP server and designed an agent for a real task, including where it needs a human.

Part 4: Production and the Enterprise

Take it from prototype to something you would put your name on.

  1. Module 11: Fine-tuning and model customization: Fine-tuning vs RAG vs prompting: the decision framework. Full fine-tuning vs parameter-efficient methods. Data preparation. The cost and maintenance trade-offs nobody mentions in the blog posts.
  2. Module 12: Running AI inside your own walls: The fastest-growing enterprise requirement in AI, and one very few engineers can meet. Why enterprises are pulling AI back inside the perimeter. Hosted vs self-hosted and open-weight models. Deploying with no route to the public internet. Keeping data, embeddings, and vector stores inside the boundary. What you give up, what you gain, and how to have that conversation with a client.
  3. Module 13: LLMOps and production readiness: Building an evaluation harness, and why you build it before the feature. Monitoring model behavior over time. Versioning prompts as the artifacts they are. Controlling inference cost before finance does it for you.
  4. Module 14: AI security and responsible AI: Prompt injection and jailbreaks from the defender's side. Data leakage and privacy risk. Guardrails and human-in-the-loop review. Bias, fairness, and setting expectations you can meet.
  5. Module 15: Capstone: Design the assistant. Build it against a real task. Present the architecture to the group. Demo, review, and critique. You leave with the system, the code, and the reasoning behind both.

By the end of Part 4 you can take an AI system from idea to production. You know how to deploy it, secure it, monitor it, control its cost, and defend your architectural decisions to engineering leaders, security teams, and clients. You are no longer experimenting with AI. You are operating it.

AI Learning Series – Practical AI skills for every level of your organisation

Tier 1: AI Foundations 

3 hours · 2 workshops 

W1.1 — What is AI (Really?) 

Cut through the hype and build a clear, grounded understanding of what AI is, how it works, and where it can — and cannot — be applied in your organisation. Participants explore the difference between AI, machine learning, generative AI, and large language models, and learn how to evaluate AI tools with confidence. 

 

W1.2 — How Generative AI Works 

Go deeper into generative AI — how it produces outputs, why hallucinations happen, and what that means for safe use at work. Participants build their first repeatable AI workflow templates and leave with a proven prompting framework they can apply immediately. 

 

Tier 2: AI Productivity 

4.5 hours · 3 workshops 

W2.1 — Building Your AI Toolkit 

Explore the landscape of AI tools available today and learn how to choose the right one for any given task or risk profile. Participants leave with a personal AI toolkit matched to their role and day-to-day responsibilities. 

W2.2 — Identifying AI Workflow Use Cases 

Learn to spot high-value AI opportunities within existing workflows using a structured prioritisation approach. Participants apply the Assist · Automate · Optimise classification model and complete a Value × Feasibility portfolio exercise for their own team context. 

W2.3 — Designing Agentic AI-Enabled Workflows 

Move from individual AI tasks to end-to-end agentic workflows. Participants design human-in-the-loop AI workflows and apply the AI Initiative Readiness Canvas to assess whether an initiative is ready to move forward — or not. 

 

Tier 3: AI for Strategic Leaders 

4.5 hours · 3 workshops 

W3.1 — AI Operating Model & Readiness 

Assess your organisation’s readiness across five key pillars and determine the right AI operating model for your context — including whether to build, buy, or partner. Participants map AI value drivers to business KPIs and choose the right Centre of Excellence model for their organisation. 

W3.2 — AI Strategy & Investment 

Move from AI curiosity to a credible, sequenced investment roadmap. Participants build an H1/H2/H3 strategic AI roadmap, prioritise initiatives against business outcomes, and develop the language and frameworks to make confident AI investment decisions. 

W3.3 — AI Risk, Governance & Ethics 

Understand the governance landscape and build a framework for responsible AI deployment. Participants explore key regulatory frameworks including the EU AI Act, NIST RMF, and ISO 42001, and leave with a governance posture appropriate for their organisation's risk profile. 

Generative AI Boot Camp – Insurance

Module 1: GenAI 101 for Insurance

  • LLM fundamentals (transformers, context, hallucinations)
  • Insurance-specific use cases:
  • Underwriting decision support
  • Claims automation and summarization
  • Fraud detection insights
  • Policy document generation and analysis
  • Customer service automation (chatbots, call summaries)
  • Risks: bias in underwriting, regulatory violations, data privacy

Hands-on Lab: Identify 5 high-value use cases (e.g., claims triage, underwriting risk scoring); 

classify by risk, compliance impact, and ROI

Module 2: Governance, Compliance & Model Risk

  • Regulatory landscape (NAIC guidelines, data privacy laws, internal compliance)
  • Model risk management (MRM) and explainability
  • AI ethics: fairness, bias detection, auditability

Workshop: Create an Insurance AI Governance Framework including:

  • Acceptable use policies, Model validation checkpoints, Audit trails and explainability requirements

Module 3: Prompt Engineering for Insurance Workflows

  • Prompt design for business scenarios:
  • Claims summarization
  • Underwriting analysis
  • Policy interpretation
  • Human-in-the-loop validation patterns

Lab: Use prompts to:

  • Summarize claims documents
  • Generate underwriting insights
  • Draft policy explanations for customers

Module 4: AI for Engineering & Product Development

  • AI-assisted development (Copilot, code generation)
  • Accelerating API development for insurance platforms
  • Documentation automation for compliance

Lab: Generate:

  • Claims processing API
  • Test cases and documentation using AI tools

Module 5: AI in SDLC & DevOps

  • AI integration across:
  • Requirements → user stories → acceptance criteria
  • Code → testing → deployment
  • Traceability and auditability in regulated environments

Lab: Use AI to:

  • Convert business requirements into user stories and test cases
  • Generate code and track outputs for compliance

Module 6: Testing, QA & Validation

  • AI-assisted testing:
  • Test case generation
  • Edge case detection
  • Regression automation
  • Validation requirements for insurance systems

Lab: Generate and execute:

  • Test scenarios for claims workflows
  • Validate underwriting rules

Module 7: DevOps, Observability & Risk Monitoring

  • AI-enhanced monitoring and anomaly detection
  • Detecting fraud patterns and system anomalies
  • AI-assisted incident management

Lab: Simulate:

  • Fraud detection scenario
  • AI-driven anomaly analysis

Module 8: Data, RAG & Intelligent Insurance Systems

  • Retrieval-Augmented Generation (RAG) for:
  • Policy documents
  • Claims history
  • Regulatory guidelines
  • Secure data access and governance

Lab: Build a RAG-based assistant for:

  • Claims adjusters
  • Underwriters

Module 9: Adoption Strategy, Metrics & Scaling

  • AI adoption roadmap:
  • Pilot → scale → enterprise rollout
  • Organizational readiness and change management
  • KPIs:
  • Claims processing time reduction
  • Loss ratio improvement
  • Customer satisfaction (NPS)
  • Fraud detection accuracy

Workshop: Create a 90-day AI adoption roadmap for:

  • Claims
  • Underwriting
  • Customer experience

Generative AI Boot Camp – Manufacturing

Module 1: GenAI 101 for Manufacturing

  • LLM fundamentals (transformers, context, hallucinations)
  • Manufacturing-specific use cases:
  • Predictive maintenance and asset monitoring
  • Production planning and scheduling optimization
  • Quality inspection and defect analysis
  • Digital work instructions and SOP automation
  • Supply chain demand forecasting
  • Risks: safety, operational downtime, data leakage, system reliability

Hands-on Lab: Identify 5 high-value use cases (e.g., predictive maintenance, quality 

automation); classify by risk, operational impact, and ROI

Module 2: Governance, Compliance & Safety

  • Industry regulations (ISO standards, OSHA, quality compliance)
  • Cybersecurity in manufacturing (OT/IT convergence risks)
  • AI governance frameworks (model validation, auditability)

Workshop: Create a Manufacturing AI Governance Framework including:

  • Safety controls and human oversight
  • Data classification and usage policies
  • Operational risk mitigation strategies

Module 3: Prompt Engineering for Operations

  • Prompt design for manufacturing scenarios:
  • Root cause analysis
  • Equipment troubleshooting
  • Production optimization
  • Human + AI collaboration in shop floor environments

Lab: Use prompts to:

  • Diagnose equipment issues
  • Generate corrective actions
  • Summarize production reports

Module 4: AI for Engineering & Development

  • AI-assisted coding for manufacturing systems (MES, ERP integrations)
  • Automating technical documentation (SOPs, work instructions)
  • Legacy system modernization

Lab: Generate:

  • API for production tracking
  • Automated documentation for processes

Module 5: AI in SDLC & DevOps

  • Integrating AI across:
  • Requirements → engineering design
  • Development → testing → deployment
  • Traceability in regulated manufacturing environments

Lab: Use AI to:

  • Convert production requirements into system features
  • Generate code and validation artifacts

Module 6: Testing, QA & Quality Assurance

  • AI-assisted quality testing:
  • Defect detection
  • Test case generation
  • Regression testing
  • Quality assurance in manufacturing systems
  • Lab: Generate and execute:
  • Test cases for production workflows
  • Quality validation scenarios

Module 7: DevOps, Observability & Smart Factory

  • AI-driven monitoring and anomaly detection
  • Predictive analytics for equipment and production lines
  • Incident detection and resolution

Lab: Simulate:

  • Production anomaly detection
  • AI-driven root cause analysis

Module 8: Data, RAG & Intelligent Manufacturing

  • RAG with:
  • Machine sensor data
  • Maintenance logs
  • Supply chain data
  • Secure data access across systems (MES, ERP, IoT platforms)

Lab: Build a RAG-based assistant for:

  • Maintenance engineers
  • Production supervisors

Module 9: Adoption Strategy, Metrics & Scaling

  • AI adoption roadmap:
  • Pilot → scale → enterprise rollout
  • IT/OT alignment and workforce readiness
  • KPIs:
  • Downtime reduction
  • Yield improvement
  • Quality defect reduction
  • Supply chain efficiency

Workshop: Create a 90-day AI adoption roadmap for:

  • Production
  • Maintenance
  • Supply chain

Generative AI Boot Camp – Utilities

Module 1: GenAI 101 for Utilities

  • LLM fundamentals (transformers, context, hallucinations)
  • Utilities-specific use cases:
  • Grid load forecasting
  • Outage prediction and restoration support
  • Asset maintenance insights (predictive maintenance)
  • Customer service automation (billing, outage inquiries)
  • Regulatory reporting automation
  • Risks: grid reliability, safety, cybersecurity, data exposure

Hands-on Lab: Identify 5 high-value use cases (e.g., outage management, asset monitoring); 

classify by risk, regulatory impact, and ROI

Module 2: Governance, Compliance & Security

  • NERC CIP compliance considerations
  • Data privacy (customer data, smart meter data)
  • Cybersecurity risks in critical infrastructure
  • AI governance frameworks (model risk, auditability)

Workshop: Create a Utility AI Governance Framework including:

  • Allowed/blocked use cases
  • Data classification policies
  • Human-in-the-loop controls

Module 3: Prompt Engineering & Operational Decision Support

  • Prompt design for operational scenarios
  • AI-assisted troubleshooting and incident response
  • “Human + AI” collaboration for grid operators

Lab: Use prompts to:

  • Analyze outage scenarios
  • Generate restoration plans
  • Summarize field reports

Module 4: AI for Engineering & Development (Copilot / Automation)

AI-assisted coding for utility systems (SCADA integrations, APIs)

Documentation automation for compliance and audits

Code modernization (legacy systems → cloud)

Lab: Generate:

  • API service for outage reporting
  • Unit tests and documentation using AI tools

Module 5: AI in the Utility SDLC & DevOps

  • Integrating AI into:
  • Requirements (use case modeling)
  • Development (code generation)
  • Testing (automation)
  • Deployment (CI/CD pipelines)
  • Ensuring traceability for regulated environments

Lab: Use AI to:

  • Convert requirements into test cases and code
  • Track outputs for compliance and audit

Module 6: Testing, QA & Reliability

  • AI-assisted test generation (functional, regression, edge cases)
  • Testing critical infrastructure systems
  • Reliability and resilience testing

Lab: Generate and execute:

  • Test scenarios for outage management systems
  • Performance and reliability validation

Module 7: DevOps, Observability & Grid Reliability

  • AI-enhanced monitoring and alerting
  • Predictive anomaly detection in grid systems
  • Incident management with AI insights

Lab: Simulate:

  • Grid anomaly detection
  • AI-driven root cause analysis

Module 8: Data, RAG & Smart Grid Intelligence

  • Using Retrieval-Augmented Generation (RAG) with:
  • Asset data
  • GIS systems
  • Smart meter data
  • Secure data access and governance

Lab: Build a RAG-based assistant for:

  • Asset maintenance queries
  • Field technician support

Module 9: Adoption Roadmap & Metrics

  • AI adoption strategy for utilities:
  • Pilot → scale → enterprise rollout
  • Organizational readiness (IT + OT alignment)

KPIs:

  • Outage reduction time
  • Customer satisfaction
  • Maintenance cost savings
  • Operational efficiency

Workshop: Create a 90-day AI adoption roadmap for:

  • Grid operations
  • Customer experience
  • Asset management

Generative AI Boot Camp – Pharma

Module 1: GenAI 101 for Biopharma 

  • LLMs/transformers, context windows, grounding/RAG, hallucinations.
  • High-value biopharma use cases: protocol parsing, validation docs, SOP helpers, QMS 
  • tooling, CSV test scaffolds, PV triage, MFG exception analysis.
  • Risks: data leakage, IP, bias, safety.

Hands-on Lab: Identify 5 internal use cases; classify by value/risk; map to guardrails.

Module 2: Compliance & Guardrails 

  • GxP/Part 11, data residency, access control, audit trails, model risk tiers.
  • “Allow/deny” patterns, red-team prompts, record retention & attribution.

Workshop: Draft a 1-page team “AI Use Policy” + prompt safety checklist.

Module 3: Prompt Engineering & Vibe Coding 

  • Task decomposition, role prompting, chain-of-thought proxies, critique loops.
  • Vibe coding patterns: co-creation sessions, driver/navigator with AI, guardrail breaks, 
  • acceptance criteria alignment.

Lab: Turn a user story into design notes, stubs, and tests via vibe coding.

Module 4: GitHub Copilot Essentials 

  • Copilot Chat, inline completions, test generation, code refactors, doc blocks.
  • Repo policy, telemetry settings, secret hygiene, license/IP considerations.

Lab: Demo Copilot in a sandbox repo; generate a service + unit tests; log what was AI-generated 

for audit.

Module 5: AI in the SDLC 

  • Requirements → acceptance criteria → code → tests → docs → reviews.
  • Traceability with issues/PRs; storing prompts/outputs as validation artifacts.

Lab: How can you use AI to aid value delivery in your lifecycle?

Module 6: Testing, QA & Validation 

  • AI for unit/integration tests, boundary & property tests, mutation testing.
  • CSV/CSA alignment: objective evidence, independence, change control.

Lab: Generate test suites with Copilot, run, capture evidence in pipeline.

Module 7: DevOps, CI/CD & Observability

  • AI-assisted pipelines (lint, SAST/DAST, SBOM), policy-as-code, gated deploys.
  • ChatOps for PR review and post-deploy checks.

Lab: Add AI-generated pipeline steps; enforce policy gates; store build artifacts for audit.

Module 8: RAG, Data Safety & Domain Grounding 

  • Safe retrieval (vector stores, ACLs), PHI/PII handling, prompt shielding.
  • When to prefer patterns over free-form generation (templates, controlled gen).

Lab: Demo a RAG helper showcasing how agents can support delivery

Module 9: Adoption Plan, Metrics & Next Steps 

  • Roles & responsibilities, ambassador model, training paths, sandbox → pilot → scale.
  • KPIs: lead time, escaped defects, validation effort saved, rework, security findings.

Leading the AI-Native Organization

  • AI Orientation for Leaders – Building AI intuition to support sound decision‑making 
  • The Current State of AI Adoption – Understanding the AI Chasm and why most organisations fail to realise value 
  • The AI‑Native Organization Model – Organisational Catalysts, Enabling Capabilities, AI‑Empowered Agility, and Human‑Centric AI Culture 
  • AI Money Map – Connecting AI initiatives to business outcomes through value‑led prioritisation 
  • Five AI Value Patterns – Knowledge & decision support, customer interaction, workflow automation, risk & control, and expert productivity 
  • AI Strategic Intent & Vision – Defining the business bets your organisation will make on AI 
  • AI‑Native Workforce – Distributed AI fluency, change agents, and leadership responsibilities 
  • Human‑Centric AI Culture – Building trust, psychological safety, and augmentation‑first adoption 
  • AI‑Empowered Agility – Using agile principles to experiment, learn, and scale AI safely 
  • Curated Data – Why data quality, ownership, and accessibility determine AI success 
  • Governance & Ethics – Establishing guardrails that enable speed while managing business risk 
  • Operational AI Technology – Understanding the platforms and capabilities required to scale AI initiatives 
  • AI‑Native Leader Next Steps – Translating insights into a focused leadership action plan 

Microsoft Power Apps Boot Camp

1. Introduction to Power Apps

  • What is Power Apps?
  • Role in the Power Platform
  • Types of apps

2. Canvas Apps vs Model-Driven Apps

  • Key differences
  • When to use each type
  • Strengths and limitations

3. Licensing Requirements

  • Power Apps licenses overview
  • Dataverse usage scenarios
  • When Premium licensing is required

4. Introduction to Canvas Apps

  • Canvas app building blocks
  • Designing screens and layout

5. Working with Canvas App Controls, Power Fx & Data Connections

  • Controls and properties
  • Power Fx fundamentals
  • Connecting to data sources (SharePoint, Excel, Dataverse, etc.)
  • Building simple formulas and logic

6. Introduction to Dataverse & Model-Driven Apps

  • What is Dataverse?
  • Tables, columns, relationships
  • Overview of model-driven design principles

7. Creating Solutions and Tables in Dataverse

  • What are Solutions?
  • Creating custom tables and relationships
  • Option sets, lookups, and data types
  • Understanding primary keys and schema design

8. Creating Model-Driven Apps

  • App design and components
  • Navigation, sitemap, and app configuration
  • Adding forms, views, dashboards

9. Creating and Working with Forms & Views in Model-Driven Apps

  • Form types and customization
  • Business rules and visibility settings
  • View creation and filtering

10. Publishing & Sharing Model-Driven Apps

  • App validation and publishing
  • Sharing apps and managing permissions

Practical Microsoft Copilot for Real Work

Module 1 — Copilot Basics

  • What is Microsoft Copilot?
  • Licensing and prerequisites
  • Prompting fundamentals

Module 2 — Using Copilot in Office Apps

  • Copilot in Word: drafting, summarizing, improving content
  • Copilot in Excel: insights, formulas, visualizations
  • Copilot in PowerPoint: slide generation and editing
  • Copilot in Outlook: email summaries and drafting

Module 3 — Copilot in SharePoint

  • Using Copilot with document libraries

Module 4 — Copilot Chat in Teams

  • Meeting recaps and action items
  • Summarizing chat history

Module 5 — Work Copilot vs Web Copilot

  • Differences between Work Copilot and Web Copilot
  • Generative AI Capabilities

Module 6 — Creating Copilot Agents in Teams

  • Connecting data sources
  • Publishing an Agent to Teams

AI Agents with Google’s ADK Bootcamp

Part1: Intro to Agents & ADK

  • What are AI agents and why now?
  • ADK core concepts (agent, tool, memory, workflow)
  • Demo: adk init structure walkthrough
  • Hands-on: Create your first agent
  • Discussion: Agent use cases
  • Q&A

Part 2: Models and Tools

  • Connecting to Gemini via Vertex AI
  • Using open models via LiteLLM
  • Defining Python tools and schemas
  • Demo: Agents in action with Gemini + tool use
  • Hands-on: Create a Python tool and link it to your agent
  • Q&A

Part 3: Memory and Multimodality

  • Conceptual flow and memory persistence
  • Types of memory: buffer, summary
  • Implementing memory in ADK
  • Hands-on: Add memory and interact using adk web
  • Discussion: What agents should remember
  • Q&A

Part 4: Agentic Design Patterns

  • RAG and beyond: why patterns matter
  • Demo: Search + LLM retrieval
  • Hands-on: Implement a design pattern of choice
  • Group share: favorite patterns and use cases
  • Q&A

Part 5: Building the Full Agent

  • Review core building blocks
  • Hands-on: Create a "Daily Briefing Agent"
  • Discussion: Day 1 highlights and blockers
  • Q&A

Part 6: MCP and Agent-to-Agent Protocols

  • MCP and A2A intro
  • Use cases for multi-agent systems
  • Demo: Make your agent A2A-compatible
  • Hands-on: Swap tools, connect to MCP server
  • Discussion: Multi-agent  architectures
  • Q&A

Part 7: Agent Evaluation and AgentOps

  • Evaluation strategies for agents
  • AgentOps overview: lifecycle, CI/CD, logging, testing
  • Demo: adk run -v, agent engine, deployment paths
  • Hands-on: Analyze logs, prep for deployment
  • Q&A

Part 8: Agent Security & Wrap-Up

  • Security risks: prompt injection, tool misuse, data leakage
  • ADK mitigation strategies
  • Project: Identify one or two risks that apply directly to the agent you’ve conceptualized or built; explore the different capabilities in ADK to secure your agent.
  • Hands-on: Identify and address risks in your agent
  • Final Q&A + Certification Badge Instructions