Course Outline
Phase 1 — Introduction to Claude Code — 30 minutes
- Overview of Claude and how Claude Code differs from standard chat interfaces
- Quick orientation: We will be using the Claude app today (web or desktop); CLI and other interfaces are detailed in the reference card
- Interface walkthrough: Initiating a coding session and understanding the workspace
- Understanding Claude Code’s logic: The describe → plan → act → review cycle
- Permission management: Why Claude requests confirmation before creating files or executing code
- First project: Instructing Claude to generate a simple styled webpage from a single-sentence description
- Refining results: Instructions such as “make the header larger,” “change the colour scheme,” or “add a navigation bar”
- Guided exercise: Participants initiate a session to build a personalised “About Me” webpage, refining it through subsequent instructions
Objective: To ensure all participants overcome the initial barrier and feel at ease with the interface.
Break — 7 minutes
Phase 2 — Creating Practical Applications with Natural Language — 55 minutes
Three progressively complex tasks completed solely using natural language prompts.
- Task 1 — Interactive dashboard: A styled dashboard featuring sample data, charts, and statistics. Practise providing design direction such as “use a dark theme,” “add a sidebar,” or “make it responsive.”
- Task 2 — Data analysis: Provide a sample CSV file and ask Claude to summarise data, identify trends, find highs/lows, and generate a visual chart. This demonstrates Claude writing and executing code on your behalf.
- Task 3 — Automation tool: Build 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 highlights Claude’s background actions: files created, code written, and how to interpret the output. Participants record their most effective prompts in a shared Prompt Playbook.
Break — 7 minutes
Phase 3 — Optimising Your Workflow with Claude Code — 35 minutes
- The art of effective prompting: Distinguishing between specific and vague instructions
- Live demonstration: A side-by-side comparison of weak versus strong prompts applied to the same task
- Iteration and refinement: Requesting explanations of choices, undoing changes, or trying alternative approaches
- Working with uploaded files: Tasks such as “read this document and summarise it” or “convert this spreadsheet into a chart”
- Multi-step workflows: Chaining requests to create complex outputs
- Understanding costs and usage: Explaining tokens, context windows, and subscription tiers
- Determining when to use Claude Code versus standard Claude chat
- Guided exercise: Participants extend a Phase 2 project with a new feature using a multi-step prompt, then compare before-and-after prompts to identify key differences
Objective: To move beyond “it works” to achieving consistent, high-quality results.
Break — 7 minutes
Phase 4 — Integrating Claude with Your Tools via MCP — 34 minutes
Pre-class preparation: Participants received instructions via email to connect Gmail or Google Drive before the session, allowing classroom time to focus on using the connection rather than authenticating.
- Introduction to MCP (Model Context Protocol): The universal integration system for AI tools
- The value of MCP: Transforming Claude from a chat assistant into a connected workflow hub
- The Connectors Directory: Browsing and adding integrations directly within the Claude app
- Desktop Extensions: One-click installations (for Claude Desktop users)
- Live demonstration (single workflow): “Check my Google Calendar for tomorrow’s meetings and draft a prep email for each”
- Guided exercise: Participants use their pre-connected service (or connect one live) to assign a task to Claude, e.g., “Read my recent emails about project updates and create a summary document”
- Key concepts: OAuth, permissions, managing tool access per conversation, security awareness, and locating new connectors
Objective: To help participants view Claude as a connective layer, rather than just a coding tool.
Phase 5 — Capstone Project & Conclusion — 35 minutes
Capstone mini-project (25 min): Each participant selects one scenario:
- A polished landing page or portfolio site
- A data analysis pipeline: Upload a file, analyse it, and produce a visual report
- An interactive tool solving a specific problem in their workflow
- A connected workflow: Retrieve data from the service connected in Phase 4, transform it, and generate a deliverable
The instructor circulates to assist with prompt refinement and highlights standout examples.
Wrap-up (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 — understanding what each unlocks and which fits which use case
- Recommended resources: Official documentation, Anthropic’s prompt engineering guide, and community channels
- Participants leave with a reference card covering prompting patterns, connector setup, and useful MCP integrations
Requirements
Entry Requirements
Essential Knowledge
- Basic computer proficiency: navigating files and folders, operating a web browser, and installing software
- General familiarity with AI assistants (e.g., casual use of ChatGPT, Gemini, or Claude is beneficial context, though not mandatory)
Experience Expectations
- No coding, programming, or terminal experience is needed. This course is tailored for individuals who have never written a line of code.
- No prior experience with Claude or other AI tools is necessary.
Technical Specifications
- Participants should bring a laptop (Mac, Windows, or Linux) equipped with a modern web browser
- A stable internet connection
- A Claude Pro subscription for the duration of the session (a 1-month gift subscription is included with course registration; setup instructions are provided before class)
- Claude Desktop is suggested but not mandatory (the web interface at claude.ai is sufficient for all exercises)
- A Google account is recommended for the MCP connectors exercise (Gmail, Google Drive, Google Calendar), though alternative connector options are available
Target Audience
- Business professionals aiming to enhance productivity and automation through AI
- Marketing specialists, operations managers, and analysts seeking to automate repetitive tasks
- Founders and entrepreneurs who wish to build prototypes without hiring a developer
- Educators and researchers exploring AI-assisted workflows
- Individuals curious about what Claude can build, regardless of their 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