Course Outline
Phase 1 — Getting Started with Claude Code — 30 minutes
- An overview of Claude and the distinctions between Claude Code and standard chat
- Initial orientation: focusing on the Claude app (web or desktop) for today’s session; the 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: the rationale behind Claude seeking confirmation before creating files or executing code
- First project: instructing Claude to generate a simple styled webpage from a single-sentence description
- Refining outputs: issuing instructions such as “resize the header,” “update the color palette,” or “insert a navigation bar”
- Guided exercise: participants initiate a session to create a personalized “About Me” webpage, improving it through subsequent instructions
Objective: overcome initial barriers and gain comfort with the interface.
Break — 7 minutes
Phase 2 — Creating Practical Applications with Natural Language — 55 minutes
Three tasks of increasing complexity, driven solely by natural language prompts.
- Task 1 — Interactive dashboard: a styled dashboard incorporating sample data, charts, and statistics. Focus on providing design directives like “apply a dark theme,” “include a sidebar,” or “ensure responsiveness.”
- Task 2 — Data analysis: supply a sample CSV and request that Claude summarize data, identify trends, detect peaks and troughs, and generate visual charts. This demonstrates Claude writing and executing code on your behalf.
- Task 3 — Automation tool: develop a simple utility such as a unit converter, quiz application, or budget calculator. This introduces the concept of Claude building interactive tools rather than static pages.
Following each task, the instructor will explain the backend processes: files created, code generated, and how to interpret outputs. Participants will record their most effective prompts in a shared Prompt Playbook.
Break — 7 minutes
Phase 3 — Optimizing Claude Code Usage — 35 minutes
- Effective prompting techniques: contrasting specific versus vague instructions
- Live demonstration: comparing weak and strong prompts on the same task side-by-side
- Iteration and refinement: requesting explanations, reverting changes, or exploring alternative approaches
- Handling uploaded files: tasks such as “read and summarize this document” or “convert this spreadsheet into a chart”
- Multi-step workflows: linking requests to generate complex outputs
- Cost and usage insights: understanding tokens, context windows, and subscription tiers
- Distinguishing when to use Claude Code versus standard Claude chat
- Guided exercise: participants extend a Phase 2 project with new features using multi-step prompts, then analyze the difference between initial and refined prompts
Objective: transition from “it works” to “achieving consistent high-quality results.”
Break — 7 minutes
Phase 4 — Integrating Claude with External Tools via MCP — 34 minutes
Pre-class preparation: participants received instructions to connect Gmail or Google Drive prior to the session, allowing class time to focus on utilization rather than authentication.
- Overview of MCP (Model Context Protocol): the universal integration system for AI tools
- The value of MCP: transforming Claude from a chat assistant into a central workflow hub
- Connectors Directory: discovering and adding integrations directly within the Claude app
- Desktop Extensions: one-click installation options (for Claude Desktop users)
- Live demo (single workflow): “Check my Google Calendar for tomorrow’s meetings and draft a preparation email for each”
- Guided exercise: participants utilize a pre-connected service (or connect one live) to assign a task to Claude, for example, “Read 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 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: 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 Phase 4 service, processing it, and producing a final deliverable
The instructor will provide individual assistance, help refine prompts, and highlight exemplary outcomes.
Conclusion (10 min):
- Next steps: Claude Code CLI for terminal users, VS Code extension for developers, and Cowork for knowledge workers
- Subscription tiers: comparing Free, Pro, and Max to identify the best fit for specific use cases
- Recommended resources: official documentation, Anthropic’s prompt engineering guide, and community forums
- Participants will receive a reference card detailing prompting patterns, connector setup, and essential MCP integrations
Requirements
Requirements
Foundational Knowledge
- Basic computer skills: managing files and folders, utilizing a web browser, and installing software
- General familiarity with AI assistants (while prior casual use of ChatGPT, Gemini, or Claude is beneficial, it is not mandatory)
Background Experience
- No coding, programming, or terminal experience is needed. This course is tailored for individuals who have never written code.
- No previous experience with Claude or other AI tools is required.
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 gift subscription is included upon registration; setup instructions will be provided prior to class)
- Claude Desktop is suggested but not essential (the claude.ai web app covers all exercises)
- A Google account is advised for the MCP connectors exercise (Gmail, Google Drive, Google Calendar), though alternative connector options exist
Target Audience
- Professionals seeking to enhance productivity and automation through AI
- Marketers, operations managers, and analysts aiming to automate routine tasks
- Founders and entrepreneurs looking to create prototypes without hiring developers
- Educators and researchers investigating AI-supported workflows
- Individuals with no technical background who are curious about 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