Course Outline
Phase 1 — Meet Claude Code — 30 minutes
- What Claude is, and what distinguishes Claude Code from regular chat.
- Quick orientation: we are using the Claude application today (web or desktop); the CLI and other interfaces are covered in the reference card.
- Interface tour: initiating a coding session and understanding the workspace.
- Understanding Claude Code’s thinking process: the describe → plan → act → review loop.
- Understanding permissions: why Claude requests approval before creating files or running code.
- Your first build: asking Claude to create a simple styled webpage from a one-sentence description.
- Iterating on results: instructing Claude to “make the header bigger,” “change the color scheme,” or “add a navigation bar.”
- Guided exercise: participants start a session and build a personalised “About Me” webpage, refining it through follow-up instructions.
Goal: everyone passes the initial interaction hurdle and becomes comfortable with the interface.
|
Break — 7 minutes |
Phase 2 — Building Real Things with Plain English — 55 minutes
Three progressively complex tasks using only natural language prompts.
- Task 1 — Interactive dashboard: styled dashboard with sample data, charts, and statistics. Practice providing design direction: “use a dark theme,” “add a sidebar,” “make it responsive.”
- Task 2 — Data analysis: provide a sample CSV, ask Claude to summarise, identify trends, find highs and lows, and generate a visual chart. This demonstrates Claude writing and executing code on your behalf.
- Task 3 — Automation tool: build a simple utility — unit converter, quiz app, or budget calculator. This introduces the idea that Claude can build interactive tools, not just static pages.
After each task, the instructor highlights what Claude did behind the scenes: files created, code written, and how to read the output. Participants document their best prompts in a shared Prompt Playbook.
|
Break — 7 minutes |
Phase 3 — Working Smarter with Claude Code — 35 minutes
- The art of good prompting: specific versus vague instructions.
- Live demo: side-by-side comparison of weak and strong prompts on the same task.
- Iterating and refining: asking Claude to explain choices, undo changes, or try a different approach.
- Working with uploaded files: “read this document and summarise it,” “convert this spreadsheet into a chart.”
- Multi-step workflows: chaining requests to build complex outputs.
- Understanding cost and usage: how tokens, context windows, and subscription tiers work.
- When to use Claude Code versus regular Claude chat.
- Guided exercise: participants extend one of their Phase 2 projects with a new feature using a multi-step prompt, then compare before-and-after prompts to identify what made the difference.
Goal: elevate from “it works” to “I can get great results consistently.”
|
Break — 7 minutes |
Phase 4 — Connecting Claude to Your Tools with MCP — 34 minutes
|
Pre-class: participants were emailed instructions to connect Gmail or Google Drive before the session, so classroom time is spent using the connection rather than authenticating. |
- What is MCP (Model Context Protocol)? The universal plug system for AI tools.
- Why MCP matters: turning Claude from a chat assistant into a connected workflow hub.
- The Connectors Directory: browsing and adding integrations directly from the Claude app.
- Desktop Extensions: one-click installs (for Claude Desktop users).
- Live demo (one workflow): “Check my Google Calendar for tomorrow’s meetings and draft a prep email for each one.”
- Guided exercise: participants use their pre-connected service (or connect one live) to give Claude a task — 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 where to find new connectors.
Goal: participants see Claude as a connective layer, not just a coding tool.
Phase 5 — Capstone & Wrap-Up — 35 minutes
Capstone mini-project (25 min): Each participant chooses 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 real problem from their workflow.
- A connected workflow: pull data from the service they connected in Phase 4, transform it, and produce a deliverable.
The instructor circulates, helps refine prompts, and showcases standout examples.
Wrap-up (10 min):
- Where to go from here: Claude Code CLI for terminal users, VS Code extension for developers, and Cowork for knowledge workers.
- Plans: Free vs. Pro vs. Max — what each unlocks and which fits which use case.
- Recommended resources: official docs, Anthropic’s prompt engineering guide, and community channels.
- Participants leave with a reference card covering prompting patterns, connector setup, and useful MCP integrations.
Requirements
Requirements
Understanding of
- Basic computer literacy: navigating files and folders, using a web browser, and installing applications
- General awareness of AI assistants’ functions (e.g., casual experience with ChatGPT, Gemini, or Claude is helpful context, though not required)
Experience with
- No coding, programming, or terminal experience is required. This course is designed for individuals who have never written code.
- No prior experience with Claude or any other AI tool is necessary.
Technical Requirements
- Participants must bring a laptop (Mac, Windows, or Linux) equipped with a modern web browser.
- A stable internet connection.
- A Claude Pro subscription for the session (a 1-month gift subscription is included with course registration; setup instructions are sent prior to the class).
- Claude Desktop is recommended but not mandatory (the web application 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 seeking to leverage AI for productivity and automation.
- Marketers, operations managers, and analysts who wish to automate repetitive tasks.
- Founders and entrepreneurs aiming to build prototypes without hiring a developer.
- Educators and researchers exploring AI-assisted workflows.
- Anyone curious about Claude’s capabilities who lacks 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
