Course Outline
Phase 1 — Introduction to Claude Code — 30 minutes
- Overview of Claude and what distinguishes Claude Code from standard chat interactions
- Initial setup: focusing on the Claude app (web or desktop) for this session; CLI and other interfaces are detailed in the reference card
- Interface walkthrough: initiating coding sessions and navigating the workspace
- Understanding Claude Code’s logic: the describe → plan → act → review cycle
- Permissions explained: why Claude requests confirmation before creating files or executing code
- First project: instructing Claude to generate a simple styled webpage from a single sentence
- Refining outcomes: requesting changes such as “enlarge the header,” “alter the color scheme,” or “add a navigation bar”
- Guided practice: participants initiate a session to create a personalized “About Me” webpage, refining it through subsequent instructions
Objective: Ensure all participants overcome the initial usage barrier and feel at ease with the interface.
Break — 7 minutes
Phase 2 — Creating Practical Projects with Natural Language — 55 minutes
Three tasks of increasing complexity using only natural language prompts.
- Task 1 — Interactive dashboard: creating a styled dashboard with sample data, charts, and statistics. Practice providing design feedback such as “apply a dark theme,” “insert a sidebar,” or “ensure responsiveness.”
- Task 2 — Data analysis: providing a sample CSV file and asking Claude to summarize it, identify trends, locate highs/lows, and generate visual charts. This demonstrates Claude writing and executing code on your behalf.
- Task 3 — Automation tool: developing a simple utility like a unit converter, quiz app, or budget calculator. This introduces the concept that Claude can build interactive tools, not just static pages.
Following each task, the instructor explains the 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 — Enhancing Efficiency with Claude Code — 35 minutes
- Effective prompting techniques: comparing specific versus vague instructions
- Live demonstration: side-by-side comparison of weak and strong prompts for the same task
- Iteration and refinement: requesting explanations of choices, reverting changes, or exploring alternative approaches
- Working with uploads: “Read this document and summarize it” or “Convert this spreadsheet into a chart”
- Complex workflows: linking multiple requests to create sophisticated outputs
- Cost and usage management: understanding tokens, context windows, and subscription tiers
- Decision-making: when to use Claude Code versus standard Claude chat
- Guided practice: participants enhance a Phase 2 project with a new feature using multi-step prompts, then analyze the prompt differences to identify key improvements
Objective: Progress from “it works” to achieving consistently high-quality results.
Break — 7 minutes
Phase 4 — Integrating Claude with Your Tools via MCP — 34 minutes
Pre-class preparation: Participants received instructions to connect Gmail or Google Drive beforehand, allowing classroom time to focus on usage rather than authentication.
- Understanding MCP (Model Context Protocol): The universal integration standard for AI tools
- The value of MCP: Transforming Claude from a chat assistant into a connected workflow hub
- Connectors Directory: Finding and adding integrations directly within the Claude app
- Desktop Extensions: One-click installation options (for Claude Desktop users)
- Live demonstration (single workflow): “Check my Google Calendar for tomorrow’s meetings and draft a preparation email for each”
- Guided practice: Participants use a pre-connected service (or connect one live) to assign a task to Claude, e.g., “Summarize my recent project update emails into a document”
- Key concepts: OAuth, permissions, managing tool access per conversation, security awareness, and locating new connectors
Objective: View Claude as a connective layer, not merely a coding tool.
Phase 5 — Capstone & Conclusion — 35 minutes
Capstone mini-project (25 min): Each participant selects one scenario:
- A refined landing page or portfolio site
- A data analysis pipeline: uploading a file, analyzing it, and generating a visual report
- An interactive tool addressing a specific workflow challenge
- A connected workflow: retrieving data from a service connected in Phase 4, processing it, and generating a final deliverable
The instructor will circulate to assist with prompt refinement and highlight notable examples.
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 — identifying the features and use cases for each
- Suggested resources: Official documentation, Anthropic’s prompt engineering guide, and community forums
- Takeaway: A reference card covering prompting patterns, connector configuration, and useful MCP integrations
Requirements
Requirements
Recommended Knowledge
- Basic computer skills: navigating files and folders, web browsing, and installing applications
- Familiarity with AI assistants (e.g., prior casual use of ChatGPT, Gemini, or Claude is beneficial but not mandatory)
Experience Expectations
- No coding, programming, or terminal experience is needed. This course is tailored for individuals who have never written code.
- No prior experience with Claude or other AI tools is necessary.
Technical Specifications
- A laptop (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 guides are provided in advance)
- Claude Desktop is advised but not mandatory (the web application at claude.ai is adequate for all activities)
- A Google account is suggested for the MCP connectors exercise (Gmail, Google Drive, Google Calendar), though other connector options are available
Target Audience
- Business professionals aiming to boost productivity and automation through AI
- Marketers, operations managers, and analysts seeking to automate routine tasks
- Founders and entrepreneurs wanting to create prototypes without hiring a developer
- Educators and researchers investigating AI-assisted workflows
- Individuals without a technical background who are interested in exploring Claude’s capabilities
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
