Build your capability.
Then build what’s next.

Your practical outcome: A safely configured workspace and a useful first AI-assisted task.

Required before your live Build Lab: complete the beginner pre-work materials and preparation tasks.

1. Where AI began

   Trace the journey from early AI ideas to today’s generative tools.

2. How AI has evolved

   Understand the shifts from rules and machine learning to modern assistants.

3. Large language models explained

   Learn how LLMs generate responses and why they can get things wrong.

4. The language of AI

   Decode prompts, tokens, context windows, models, agents and hallucinations.

5. Choosing your AI assistant

   Compare everyday uses of ChatGPT, Claude, Grok and Microsoft Copilot.

6. Account and workspace setup

   Set up your account, preferences and a practical workspace for learning.

7. Privacy and sharing controls

   Check data-use settings, project visibility and sharing permissions before uploading work.

8. Your first useful prompts

   Give clear instructions, context, examples and a desired output format.

9. Projects and organised context

   Keep related work, source files and instructions together where your platform supports it.

10. Working with files and sources

    Use documents as context while checking relevance, permissions and sensitive data.

11. Everyday productivity

    Apply AI to writing, summarising, planning and research with human review.

12. Reusable instructions and first skills

    Create a reusable task recipe and explore native skills where available.

13. Memory and personal context

    Build a portable context file and understand what your assistant does and does not remember.

14. Checking answers and responsible use

    Verify claims, spot weak outputs and know when a human must decide.

15. Your first practical build

    Complete and demonstrate a useful workflow for a real task.

Your practical outcome: A tested multi-step workflow with reusable skills and clear review points.

Required before your live Build Lab: complete the intermediate pre-work materials and preparation tasks.

1. From prompts to workflows

   Break a recurring task into inputs, steps, decisions and outputs.

2. Choosing the right model and mode

   Match the assistant’s capabilities, speed and cost to the job.

3. Deeper ChatGPT workflows

   Explore projects, files and supported tools for structured day-to-day work.

4. Transferring workflows across platforms

   Adapt a workflow for Claude, Grok or Copilot without assuming identical features.

5. Connectors and permissions

   Connect supported services with the minimum access needed for your task.

6. Plugins and tool extensions

   Understand platform-specific extensions and assess their permissions and reliability.

7. Designing reusable skills

   Write task instructions, examples and checks that make a skill repeatable.

8. Knowledge and memory architecture

   Separate trusted sources, working context and long-term reference material.

9. Obsidian as a knowledge workspace

   Organise linked notes and reusable knowledge to support your AI workflows.

10. Grounded research and retrieval

    Retrieve relevant information and tie outputs back to verifiable sources.

11. Structured outputs and data

    Turn messy information into useful tables, fields and consistent formats.

12. Multi-step automations

    Connect triggers, AI steps and actions with approval points.

13. Generative content workflows

    Build a repeatable process for text, images or other supported media.

14. Building a custom AI assistant

    Configure a focused assistant using an existing model, instructions, knowledge and tools.

15. Testing and demonstrating your workflow

    Measure usefulness, handle failures and present an end-to-end practical build.

Your practical outcome: A working application prototype, documented architecture and a release plan.

Required before your live Build Lab: complete the advanced pre-work materials and preparation tasks.

1. From problem to product brief

   Define users, requirements and a small, testable first release.

2. GitHub and repository setup

   Create a repository and learn commits, branches and code review.

3. Your development environment

   Set up an editor, dependencies and a repeatable local workflow.

4. Thinking in architecture

   Map the interface, server, data, integrations and trust boundaries.

5. Choosing web or mobile

   Choose a delivery approach based on users, devices and distribution needs.

6. AI-assisted application building

   Use assistants to scaffold and refine code while reviewing their changes.

7. Connecting model APIs

   Call an existing model securely and manage requests, errors and usage.

8. Data modelling and storage

   Design the records and database your application actually needs.

9. Identity and access control

   Add sign-in, roles and server-side permission checks.

10. Knowledge retrieval for applications

    Connect approved source material to grounded AI responses.

11. Tools, agents and orchestration

    Design bounded tool use with clear permissions and human approval.

12. Integrations and background jobs

    Connect external services and handle retries without duplicate actions.

13. Testing, security and evaluation

    Test behaviours, protect secrets and evaluate AI output quality.

14. Deployment and operations

    Release a prototype with monitoring, cost controls and a rollback plan.

15. Capstone and technical handover

    Demonstrate your application and document its architecture and next steps.