Course Outline
Phase 1 — Introduction to Claude Code — 55 minutes
- Overview of Claude capabilities and the specific operational distinctions of Claude Code compared to standard conversational interfaces
- Explanation of the Claude product ecosystem, including claude.ai, Claude Desktop, and the Claude Code command-line interface (CLI), and their respective roles in professional workflows
- Navigation of the Claude application interface, initiating coding sessions, and understanding the workspace architecture
- Analytical process of Claude Code: the describe → plan → act → review cycle
- Security and permissions framework: rationale for verification prompts prior to file creation or code execution
- Initial development task: directing Claude to generate a simple styled webpage based on a single-sentence requirement
- Iterative refinement techniques: modifying header dimensions, adjusting color schemes, and adding navigation elements
- Guided Exercise: Participants open the Claude application, initiate a Claude Code session, and construct a personalized profile webpage using plain language instructions. Participants practice refining outputs through iterative follow-up directives.
Objective: Ensure all participants are proficient with the interface and have successfully executed their first interaction.
Break — 10 minutes
Phase 2 — Practical Application via Natural Language — 70 minutes
This phase constitutes the primary instructional focus. Participants will complete four tasks of increasing complexity using only natural language prompts.
- Task 1 — Interactive Dashboard: Direct Claude Code to construct a styled dashboard displaying sample data with charts, metrics, and organized layout. Practice providing design specifications, such as applying dark themes, adding sidebars, and ensuring responsiveness.
- Task 2 — Data Analysis: Provide a sample CSV file and instruct Claude to summarize data, identify trends, determine extremal values, and generate visual charts. This demonstrates Claude's ability to author and execute code on behalf of the user.
- Task 3 — Document Generation: Instruct Claude to process a data file and produce a formatted report, such as a sales summary, project status update, or meeting recap. This illustrates the transformation of raw data into professional deliverables.
- Task 4 — Automation Utility: Direct Claude to build a functional tool, such as a unit converter, quiz application, or budget calculator. This introduces the capability to create interactive tools beyond static pages.
Following each task, the instructor will detail the backend processes, including file creation, code generation, and output interpretation. Participants will document optimal prompts in a shared Prompt Playbook.
Break — 10 minutes
Phase 3 — Optimizing Claude Code Efficiency — 50 minutes
- Prompt engineering best practices: the impact of specific versus vague instructions
- Live demonstration: comparative analysis of weak versus strong prompts applied to identical tasks
- Iterative refinement strategies: requesting explanations of logic, reverting changes, or exploring alternative approaches
- Processing uploaded files: summarizing documents and converting spreadsheets into visualizations
- Multi-step workflows: chaining requests to generate complex outputs (e.g., analyzing data followed by building a dashboard)
- Operational costs and usage metrics: understanding tokens, context windows, and subscription tiers
- Determining appropriate use cases for Claude Code versus standard Claude chat interfaces
- Guided Exercise: Participants select a Phase 2 project and extend it with two new features using a multi-step prompt chain. Participants will then compare pre- and post-refinement prompts to analyze effectiveness.
Objective: Advance from basic functionality to consistent, high-quality results.
Break — 10 minutes
Phase 4 — Custom Claude Workflows: Collaborative Build Session — 60 minutes
This phase transitions to collaborative group work. Rather than individual practice, the group constructs workflows together. The instructor facilitates, while participants identify real-world job-related problems, propose prompt ideas, and debate trade-offs. The objective is to develop prompt judgment by observing skilled navigation of uncertainty in real time.
The session is structured around three workflow archetypes:
- Transform — Converting input data into specified outputs (e.g., meeting notes to action items, raw data to summary emails, customer feedback to themed reports)
- Draft — Generating initial versions of content typically written from scratch (e.g., proposals, emails, job descriptions, social media posts)
- Analyze — Interrogating large documents or datasets for time-constrained review (e.g., extensive reports, survey response spreadsheets, contracts)
Setup and Framing (10 min): The instructor introduces the three archetypes and explains the session structure. Participants submit real workflow challenges from their professional roles via a shared document or chat.
Live Build #1 — Transform Workflow (20 min): The instructor selects one submitted problem and constructs the solution live, soliciting prompt ideas, objections, and refinements from the group. The instructor narrates decision-making processes. The session concludes with a reusable prompt template retained by the participant whose problem was addressed.
Live Build #2 — Draft or Analyze Workflow (20 min): Identical format, different archetype, addressing a different participant's problem.
Reflection and Review (10 min): Participants document one surprising prompting technique, one area for improvement, and one key pattern to retain. A brief group discussion follows, with 3-4 participants sharing insights. The instructor correlates observations with the broader Prompt Playbook.
Phase 5 — Integrating Claude with Tools via MCP — 50 minutes
- Definition of MCP (Model Context Protocol) as a universal interface standard for AI tool integration
- Strategic value of MCP: evolving Claude from a conversational assistant into a connected workflow hub
- The Connectors Directory: browsing and adding integrations directly within the Claude application
- Desktop Extensions: one-click installation options for Claude Desktop requiring no manual configuration
Live Demonstration: The instructor connects Claude to two services via the Connectors UI and demonstrates cross-tool workflows for government and enterprise use cases:
- “Review my Google Calendar for tomorrow's meetings and draft a preparation email for each”
- “Analyze the latest updates from our project board and write a status summary”
- “Retrieve data from this connected service and generate a local report”
Guided Exercise: Participants connect Claude to at least one service. Options are provided for varying comfort levels:
- Option A: Connect a pre-built connector from the directory (e.g., Gmail, Google Drive, or a demo service) — simple authentication and activation
- Option B: Add a custom connector by inputting an MCP server URL (instructor provides a test URL)
- Option C: Install a Desktop Extension from the marketplace (for Claude Desktop users)
Participants then assign Claude a task utilizing the connected service — for example, “Read my recent emails regarding project updates and create a summary document.”
Key concepts covered:
- Connector mechanics: OAuth authentication, permission scopes, and the nature of granted access
- Managing tool access: enabling, disabling, and controlling connector usage per conversation
- Security awareness: restricting connections to trusted services and reviewing tool permissions
- The MCP ecosystem: identifying new connectors, extensions, and community-built servers
Objective: Participants will view Claude as a connective layer for existing services, not solely as a coding tool.
Break — 10 minutes
Phase 6 — Capstone and Future Directions — 65 minutes
Capstone Mini-Project (45 min): Each participant selects one scenario and builds it with Claude:
- A polished landing page or portfolio site for a team, project, or personal brand
- A data analysis pipeline: uploading a file, analyzing it, and producing a visual report
- An interactive tool solving a specific workflow problem (calculator, tracker, converter, quiz)
- A connected workflow: retrieving data from a service, transforming it, and producing a deliverable (e.g., “read my calendar for next week and build a visual schedule”)
The instructor circulates to assist with prompt refinement and highlights exemplary outputs to the group.
Showcase and Wrap-Up (20 min):
- 6-8 participants present their builds (2-3 minutes each)
- Pathways forward: Claude Code CLI for terminal users, VS Code extension for developers, Cowork for knowledge workers
- The MCP ecosystem: locating and evaluating new connectors, extensions, and community servers
- Subscription plans: Free vs. Pro vs. Max — feature breakdowns and appropriate use cases
- Best practices summary: key Prompt Playbook patterns identified during the session
- Recommended resources: official documentation, community channels, Anthropic's prompt engineering guide
- Participants receive a reference card containing key prompting patterns, connector setup steps, and curated MCP integrations
Requirements
Requirements
Understanding of
- Basic computer literacy: navigating files and folders, using a web browser, and installing applications
- General awareness of AI assistant capabilities (e.g., casual use of ChatGPT, Gemini, or Claude is helpful context but not required)
Experience with
- No coding, programming, or terminal experience required. This course is designed for individuals who have never written code.
- No prior experience with Claude or any AI tool is necessary.
Technical Requirements
- Participants should bring a laptop (Mac, Windows, or Linux) 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 class)
- Claude Desktop is recommended but not required (the web app at claude.ai is sufficient for all exercises)
- A Google account is recommended for the MCP connectors exercise (Gmail, Google Drive, Google Calendar), but alternative connector options are available
Audience
- Business professionals seeking to leverage AI for productivity and automation
- Marketers, operations managers, and analysts aiming to automate repetitive tasks
- Founders and entrepreneurs wishing to build prototypes without hiring a developer
- Educators and researchers exploring AI-assisted workflows
- Individuals without technical backgrounds 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
