Course Summary
NotebookLM works from sources you supply, which makes it useful where general chatbots are not. This course covers building a reliable source set, interrogating it, and recognising the limits of what grounding can guarantee.
Learning Objectives
- Build a well-scoped source collection
- Query sources for grounded answers
- Generate summaries and briefings from documents
- Check answers against the underlying sources
- Recognise where grounding still fails
This course equips manufacturing teams with the practical skills to deploy AI-powered predictive maintenance systems on the factory floor. From reading sensor data to acting on AI alerts, learners will build confidence in using real-time intelligence to cut unplanned downtime, extend equipment life, and make smarter operational decisions without needing a data science background.
Learning Objectives
- Deploy sensor-based data collection pipelines for equipment monitoring
- Interpret AI-generated failure predictions and maintenance alerts
- Execute predictive maintenance workflows to reduce unplanned downtime
- Evaluate OEE impact using AI-driven operational dashboards
Course Summary
The organisational half of AI adoption, which is where most of it fails. This course covers dividing work between people and models, keeping accountability clear, and building team habits that survive after the pilot.
Learning Objectives
- Divide a workflow between human and AI effectively
- Keep accountability clear for AI-assisted output
- Verify AI work proportionate to its risk
- Introduce AI tools without eroding team skills
- Measure whether AI adoption is actually paying off
Course Summary
For developers putting Claude Code into a real codebase and workflow. This course covers configuration, extending behaviour for a specific project, and the review discipline that keeps AI-assisted changes safe to merge.
Learning Objectives
- Set up Claude Code against an existing project
- Configure project-level instructions and conventions
- Extend behaviour for team-specific workflows
- Review and verify AI-generated changes before merge
- Recognise tasks better done without AI assistance
Course Summary
Agents differ from chatbots: they take actions, not just turns. This course covers where an agent genuinely beats a script, how to scope one safely, and the guardrails a business process needs before you let software act on its own.
Learning Objectives
- Explain what separates an agent from a chatbot
- Identify processes worth automating with agents
- Design an agent workflow with clear boundaries
- Apply guardrails, approvals and human-in-the-loop checks
- Evaluate whether an agent is performing acceptably
Course Summary
A hands-on introduction to machine learning in Python. This course works through a full workflow — preparing data, training a model, and judging honestly whether the result is good enough to use.
Learning Objectives
- Prepare and clean a dataset for modelling
- Train a supervised model in Python
- Evaluate a model with appropriate metrics
- Recognise overfitting and correct for it
- Interpret and communicate model output
Course Summary
A grounding in what AI systems actually do, for people who need to make decisions about them rather than build them. This course covers how models learn, what they are reliably good and bad at, and where the real risks sit in a business context.
Learning Objectives
- Distinguish AI, machine learning and generative AI
- Explain in plain terms how a model is trained
- Identify tasks AI suits and tasks it does not
- Recognise bias, hallucination and data-privacy risks
- Assess an AI proposal for feasibility