Course Outline
Phase 1 — Introduction to Claude Code — 30 minutes
- An overview of what Claude is and how Claude Code differs from standard chat interfaces
- Quick orientation: We will utilize the Claude app (web or desktop) for this session; the CLI and other platforms are detailed in the reference card
- Interface walkthrough: Initiating a coding session and navigating the workspace
- Claude Code’s thought process: The describe → plan → act → review cycle
- Permission management: Understanding why Claude requests authorization before creating files or executing code
- First build: Instructing Claude to generate a simple styled webpage from a single-sentence description
- Refining results: Giving instructions such as “make the header bigger,” “change the color scheme,” or “add a navigation bar”
- Guided exercise: Participants initiate a session to create a personalized “About Me” webpage, refining it through subsequent instructions
Objective: Ensure all participants overcome the initial interaction barrier and feel comfortable navigating the interface.
Break — 7 minutes
Phase 2 — Creating Real Applications with Plain English — 55 minutes
Three progressively complex tasks executed using only natural language prompts.
- Task 1 — Interactive dashboard: A styled dashboard featuring sample data, charts, and statistics. Practice 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 summarize the data, identify trends, highlight highs/lows, and generate a visual chart. This demonstrates Claude writing and executing code on the user’s 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 explains the backend actions: files created, code generated, and how to interpret the output. Participants record their most effective prompts in a shared Prompt Playbook.
Break — 7 minutes
Phase 3 — Optimizing Your Work with Claude Code — 35 minutes
- The art 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 for Claude’s choices, undoing changes, or exploring alternative approaches
- Handling uploaded files: Instructing Claude to “read this document and summarize it” or “convert this spreadsheet into a chart”
- Multi-step workflows: Chaining requests to produce complex outputs
- Usage and cost awareness: Understanding tokens, context windows, and subscription tiers
- Decision-making: When to use Claude Code versus standard Claude chat
- Guided exercise: Participants extend a Phase 2 project by adding a new feature via a multi-step prompt, then compare their initial and refined prompts to understand the impact
Objective: Progress from merely getting results to consistently achieving high-quality outcomes.
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 prior to the session, allowing class time to focus on utilizing the connection rather than authentication.
- What is MCP (Model Context Protocol)? The universal integration system for AI tools
- The value 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 (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 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 best practices, and locating new connectors
Objective: 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 of the following scenarios:
- A polished landing page or portfolio site
- A data analysis pipeline: Uploading a file, analyzing it, and generating a visual report
- An interactive tool that solves a specific problem in their workflow
- A connected workflow: Retrieving data from a service connected in Phase 4, transforming it, and producing a final deliverable
The instructor circulates to assist with prompt refinement and highlights exemplary work.
Wrap-up (10 min):
- Next steps: Claude Code CLI for terminal users, the VS Code extension for developers, and Cowork for knowledge workers
- Subscription plans: Comparing Free vs. Pro vs. Max to understand what each unlocks and which suits specific use cases
- Recommended resources: Official documentation, Anthropic’s prompt engineering guide, and community channels
- Participants receive a reference card covering prompting patterns, connector setup, and useful MCP integrations
Requirements
Prerequisites
Basic Understanding of
- Fundamental computer skills: navigating files and folders, browsing the web, and installing software
- General knowledge of AI assistant capabilities (e.g., casual experience with ChatGPT, Gemini, or Claude is beneficial but not mandatory)
Experience Level
- No coding, programming, or terminal knowledge is necessary. This course is specifically tailored for individuals who have never written code.
- Prior experience with Claude or any other AI tool is not required.
Technical Requirements
- 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 provided upon course registration; setup guidelines are sent prior to the class)
- Claude Desktop is recommended but optional (the web interface at claude.ai is sufficient for all exercises)
- A Google account is advised for the MCP connectors exercise (Gmail, Google Drive, Google Calendar), though alternative connector options are available
Target Audience
- Business professionals seeking to enhance productivity and automation through AI
- Marketers, operations managers, and analysts aiming to automate repetitive tasks
- Founders and entrepreneurs looking to create prototypes without hiring developers
- Educators and researchers exploring AI-supported workflows
- Individuals curious about Claude’s capabilities, regardless of 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
