Course Outline
Phase 1 — Introduction to Claude Code — 30 minutes
- An overview of Claude and the distinct advantages of Claude Code over standard chat interactions
- Orientation: We will utilise the Claude application (web or desktop) today; the CLI and other interfaces are detailed in the reference card
- Interface walkthrough: initiating a coding session and familiarising oneself with the workspace
- Cognitive process: the describe → plan → act → review cycle used by Claude Code
- Permissions explained: why Claude requests confirmation before generating files or executing code
- First creation: instructing Claude to generate a simple styled webpage from a single-sentence description
- Refining outcomes: issuing adjustments such as “increase header size,” “modify colour scheme,” or “add a navigation bar”
- Guided activity: participants initiate a session to construct a personalised “About Me” webpage, refining it through follow-up instructions
Objective: Ensure all participants have overcome the initial learning curve and are comfortable navigating the interface.
Break — 7 minutes
Phase 2 — Creating Practical Solutions with Natural Language — 55 minutes
Three tasks of increasing complexity, executed solely through natural language prompts.
- Task 1 — Interactive dashboard: Creating a styled dashboard featuring sample data, charts, and statistics. Practise providing design directives such as “apply a dark theme,” “include a sidebar,” or “ensure responsiveness.”
- Task 2 — Data analysis: Supplying a sample CSV and asking Claude to summarise it, identify trends, locate peaks and troughs, and generate a visual chart. This demonstrates Claude writing and executing code on your behalf.
- Task 3 — Automation tool: Building a simple utility, such as a unit converter, quiz app, or budget calculator. This introduces the concept that Claude can create interactive tools, not just static pages.
Following each task, the instructor will explain the backend actions performed by Claude: files generated, code written, and how to interpret the output. Participants will record their most effective prompts in a shared Prompt Playbook.
Break — 7 minutes
Phase 3 — Optimising Workflows with Claude Code — 35 minutes
- The craft of effective prompting: comparing specific versus vague instructions
- Live demonstration: a side-by-side comparison of weak and strong prompts applied to the same task
- Iteration and refinement: requesting explanations of choices, reverting changes, or exploring alternative approaches
- Handling uploaded files: instructions like “read this document and summarise it” or “convert this spreadsheet into a chart”
- Multi-step workflows: linking requests to construct complex outputs
- Cost and usage management: an overview of tokens, context windows, and subscription tiers
- Determining when to use Claude Code versus standard Claude chat
- Guided activity: participants will expand a Phase 2 project by adding a new feature via a multi-step prompt, then compare before-and-after prompts to identify key differences
Objective: Progress from “it functions” to “I can consistently achieve high-quality results.”
Break — 7 minutes
Phase 4 — Integrating Claude with Your Tools via MCP — 34 minutes
Pre-class preparation: Participants received email instructions to connect Gmail or Google Drive prior to the session, allowing classroom time to focus on utilising the connection rather than authentication.
- Understanding MCP (Model Context Protocol): The universal connection system for AI tools
- The significance of MCP: Transforming Claude from a chat assistant into a central hub for connected workflows
- The Connectors Directory: Browsing and adding integrations directly within the Claude app
- Desktop Extensions: One-click installations (specifically for Claude Desktop users)
- Live demonstration (single workflow): “Review my Google Calendar for tomorrow’s meetings and draft a preparation email for each”
- Guided activity: participants will use their pre-connected service (or connect one live) to assign a task to Claude, for example: “Read my recent emails regarding project updates and compile a summary document”
- Key concepts: OAuth, permissions, managing tool access per conversation, security considerations, and locating new connectors
Objective: Enable participants to view Claude as a connective layer, extending beyond a mere coding tool.
Phase 5 — Capstone Project & Conclusion — 35 minutes
Capstone mini-project (25 min): Each participant will select one of the following scenarios:
- A polished landing page or portfolio site
- A data analysis pipeline: uploading a file, analysing it, and producing a visual report
- An interactive tool that addresses a specific issue in their workflow
- A connected workflow: retrieving data from the service connected in Phase 4, transforming it, and generating a deliverable
The instructor will circulate to assist with prompt refinement and highlight exemplary works.
Conclusion (10 min):
- Next steps: Claude Code CLI for terminal users, VS Code extension for developers, and Cowork for knowledge workers
- Subscription plans: Free vs. Pro vs. Max — detailing the features unlocked and the suitable use cases for each
- Recommended resources: official documentation, Anthropic’s prompt engineering guide, and community channels
- Participants will receive a reference card covering prompting patterns, connector setup, and essential MCP integrations
Requirements
Prerequisites
Foundational Understanding
- Basic digital literacy, including navigating files and folders, using a web browser, and installing applications
- A general awareness of AI assistant capabilities (familiarity with tools like ChatGPT, Gemini, or Claude is beneficial but not mandatory)
Experience Level
- No prior knowledge of coding, programming, or terminal usage is necessary. This course is tailored for individuals who have never written a line of code.
- No previous experience with Claude or other AI tools is required.
Technical Requirements
- Participants should bring a laptop (running Mac, Windows, or Linux) equipped with a current web browser
- A reliable internet connection
- A Claude Pro subscription for the duration of the session (a one-month complimentary subscription is included with registration; setup instructions will be sent prior to the class)
- Claude Desktop is suggested but not essential (the web interface at claude.ai is sufficient for all exercises)
- A Google account is recommended for the MCP connectors activity (covering Gmail, Google Drive, and Google Calendar), though alternative connector options exist
Intended Audience
- Business professionals seeking to enhance productivity and automation through AI
- Marketing specialists, operations managers, and analysts aiming to automate repetitive duties
- Founders and entrepreneurs wanting to create prototypes without engaging a developer
- Educators and researchers investigating AI-assisted processes
- Individuals curious about Claude’s capabilities who lack a technical background
Testimonials (1)
That i gained a knowledge regarding streamlit library from python and for sure i'll try to use it to improve applications in my team which are made in R shiny
