Course Outline
Phase 1 — Introduction to Claude Code — 30 minutes
- Understanding Claude and the distinctions between Claude Code and standard chat interfaces
- Quick orientation: We will utilize the Claude app (web or desktop) during this session; the CLI and other interfaces are detailed in the reference card
- Interface walkthrough: Initiating a coding session and navigating the workspace
- Claude Code’s operational logic: The describe → plan → act → review cycle
- Permission management: Why Claude requests confirmation before creating files or executing code
- First project: Instructing Claude to build a simple styled webpage from a single sentence description
- Refining outcomes: Requesting changes such as enlarging headers, adjusting color schemes, or adding navigation bars
- Guided Exercise: Participants initiate a session to create a personalized “About Me” webpage, refining it through follow-up instructions
Objective: Ensure all participants have overcome initial interaction barriers and feel comfortable with the interface.
Break — 7 minutes
Phase 2 — Creating Real Applications with Natural Language — 55 minutes
Three progressively complex tasks relying solely on natural language prompts.
- Task 1 — Interactive Dashboard: Design a styled dashboard with sample data, charts, and statistics. Practice providing design directives like “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 data, identify trends, highlight highs/lows, and generate visual charts. This demonstrates Claude writing and executing code on your behalf.
- Task 3 — Automation Utility: Create a simple tool such as a unit converter, quiz app, or budget calculator. This introduces the concept that Claude can build interactive applications, not just static pages.
Following each task, the instructor explains the background processes: 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 Workflows with Claude Code — 35 minutes
- Effective prompting techniques: Differentiating between specific and vague instructions
- Live demonstration: Side-by-side comparison of weak versus strong prompts for the same task
- Iteration and refinement: Asking Claude to explain choices, revert changes, or adopt alternative approaches
- File handling: Commands such as “read this document and summarize it” or “convert this spreadsheet into a chart”
- Multi-step workflows: Chaining requests to construct complex outputs
- Usage and cost management: Understanding tokens, context windows, and subscription tiers
- Choosing between Claude Code and standard Claude chat
- Guided Exercise: Participants expand a Phase 2 project with a new feature using multi-step prompts, then compare prompt variations to identify effectiveness factors
Objective: Progress from basic functionality to consistently achieving 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 class time to focus on usage rather than authentication.
- Understanding MCP (Model Context Protocol): The universal interface for AI tool integrations
- The value of MCP: Evolving Claude from a chat assistant into a connected workflow hub
- The Connectors Directory: Discovering 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 preparation emails for each one”
- Guided Exercise: Participants use their pre-connected service (or connect one live) to assign a task to Claude, such as “Read my recent emails regarding project updates and create a summary document”
- Core Concepts: OAuth, permissions, managing tool access per conversation, security considerations, and locating new connectors
Objective: Recognize Claude as a connective layer rather than solely a coding tool.
Phase 5 — Capstone & Conclusion — 35 minutes
Capstone Mini-Project (25 min): Each participant selects one of the following scenarios:
- 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 real-world workflow problem
- A connected workflow: Retrieving data from a Phase 4 service, transforming it, and producing a final deliverable
The instructor circulates the room, assisting with prompt refinement and highlighting exceptional examples.
Conclusion (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, Pro, and Max tiers to determine the best fit for specific use cases
- Recommended Resources: Official documentation, Anthropic’s prompt engineering guide, and community channels
- Participants depart with a reference card detailing prompting patterns, connector setup, and essential MCP integrations
Requirements
Prerequisites
Familiarity With
- Basic computer skills: managing files and folders, navigating web browsers, and installing software
- A general understanding of AI assistant capabilities (prior casual use of ChatGPT, Gemini, or Claude is beneficial but not mandatory)
Required Experience
- No coding, programming, or terminal experience is necessary. This course is specifically tailored for individuals who have never written code.
- No prior experience with Claude or other AI tools is required.
Technical Requirements
- A laptop (running Mac, Windows, or Linux) equipped with a current web browser
- A stable internet connection
- A Claude Pro subscription for the duration of the session (a one-month complimentary subscription is included upon registration, with setup instructions sent prior to the class)
- Claude Desktop is suggested but not mandatory (the claude.ai web application 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 provided
Target Audience
- Business professionals seeking to enhance productivity and automation through AI
- Marketing specialists, operations managers, and analysts aiming to automate repetitive tasks
- Founders and entrepreneurs looking to create prototypes without hiring a developer
- Educators and researchers interested in AI-assisted workflows
- Individuals curious about Claude’s capabilities without 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
