Course Outline
Phase 1 — Introduction to Claude Code — 55 minutes
- Understanding what Claude is and how Claude Code differs from standard chat.
- Overview of the Claude product family: claude.ai, Claude Desktop, Claude Code (CLI), and their relationships.
- Interface tour: navigating the Claude app, initiating a coding session, and understanding the workspace.
- Comprehending Claude Code’s logic: the describe → plan → act → review cycle.
- Understanding permissions: why Claude requests approval before creating files or executing code.
- Your first build: instructing Claude to create a simple styled webpage from a one-sentence description.
- Refining results: instructions like “make the header larger,” “change the color scheme,” “add a navigation bar.”
- Guided exercise: Participants open the Claude app, start a Claude Code session, and build a personalized “About Me” webpage by describing their requirements in plain English. They practice refining outputs through follow-up instructions.
Objective: Ensure everyone is comfortable with the interface and overcomes the initial learning curve.
Break — 10 minutes
Phase 2 — Creating Real Projects with Natural Language — 70 minutes
This section forms the core of the morning. Participants complete four tasks of increasing complexity using only natural language prompts.
- Task 1 — Interactive dashboard: Instruct Claude Code to create a styled dashboard displaying sample data with charts, statistics, and a clean layout. Practice providing design directives: “use a dark theme,” “add a sidebar,” “make it responsive.”
- Task 2 — Data analysis: Provide Claude with a sample CSV file and ask it to summarize the data, identify trends, locate highest and lowest values, and generate a visual chart. This demonstrates how Claude writes and executes code on your behalf.
- Task 3 — Document generator: Instruct Claude to read a data file and produce a formatted report — such as a sales summary, project status update, or meeting recap. This shows how Claude transforms raw data into polished deliverables.
- Task 4 — Automation tool: Instruct Claude to build a simple utility — a unit converter, quiz app, or budget calculator. This introduces the concept that Claude can create interactive tools, not just static pages.
After each task, the instructor explains Claude’s backend actions: which files were created, what code was written, and how to interpret the output. Participants document their most effective prompts in a shared Prompt Playbook.
Break — 10 minutes
Phase 3 — Working Smarter with Claude Code — 50 minutes
- The craft of effective prompting: specific versus vague instructions.
- Live demo: side-by-side comparison of weak and strong prompts for the same task.
- Iterating and refining: asking Claude to explain its choices, undo changes, or attempt alternative approaches.
- Working with uploaded files: “read this document and summarize it,” “convert this spreadsheet into a chart.”
- Multi-step workflows: chaining requests to create complex outputs (“first analyze this data, then build a dashboard from the results.”)
- Understanding cost and usage: how tokens, context windows, and subscription tiers function.
- Determining when to use Claude Code versus regular Claude chat.
- Guided exercise: Participants select one Phase 2 project and extend it with two new features using a multi-step prompt chain. They then compare their before-and-after prompts to identify what drove the improvement.
Objective: Elevate skills from “it works” to “I can achieve great results consistently.”
Break — 10 minutes
Phase 4 — Your Claude Workflows: Live Build Session — 60 minutes
This phase shifts the energy in the room. Instead of individual practice, the group collaborates. The instructor leads, but participants direct the process by presenting real problems from their jobs, suggesting prompt ideas, and debating tradeoffs. The goal is to learn prompt evaluation by observing an expert navigate uncertainty in real-time.
Three workflow archetypes structure the session:
- Transform — take input X, produce output Y (meeting notes → action items; raw data → summary email; customer feedback → themed report)
- Draft — generate a first version of something you would typically write from scratch (proposals, emails, job descriptions, social media posts)
- Analyze — interrogate a document or dataset you lack time to review carefully (a 40-page report, a spreadsheet of survey responses, a contract)
Setup and framing (10 min): The instructor introduces the three archetypes and explains the session format. Participants submit real workflow problems from their jobs via a shared doc or chat.
Live build #1 — Transform workflow (20 min): The instructor selects one submitted problem, builds it live while the group suggests prompts, pushbacks, and refinements. The instructor narrates every decision. The session concludes with a working prompt template that the participant whose problem was chosen keeps.
Live build #2 — Draft or Analyze workflow (20 min): Same format, different archetype, different participant’s problem.
Reflection & share-back (10 min): Participants jot down one prompting move that surprised them, one thing they would do differently, and one pattern they plan to use going forward. A quick group share follows — 3-4 voices, not everyone. The instructor connects these observations to the broader Prompt Playbook.
Phase 5 — Connecting Claude to Your Tools via MCP — 50 minutes
- What is MCP (Model Context Protocol)? The universal integration system for AI tools.
- Why MCP matters: transforming Claude from a chat assistant into a connected workflow hub.
- The Connectors Directory: browsing and adding integrations directly from the Claude app.
- Desktop Extensions: one-click installs for Claude Desktop (no configuration files needed).
Live demo: The instructor connects Claude to two services through the Connectors UI and demonstrates cross-tool workflows:
- “Check my Google Calendar for tomorrow’s meetings and draft a prep email for each one.”
- “Read the latest updates from our project board and write a status summary.”
- “Pull data from this connected service and build a local report from it.”
Guided exercise: Participants connect Claude to at least one service. Options are provided for different comfort levels:
- Option A: Connect a pre-built connector from the directory (e.g., Gmail, Google Drive, or a demo service) — click, authenticate, and go.
- Option B: Add a custom connector by pasting an MCP server URL (the instructor provides a test URL).
- Option C: Install a Desktop Extension from the marketplace (for Claude Desktop users).
Participants then assign Claude a task that utilizes the connected service — e.g., “Read my recent emails about project updates and create a summary document.”
Key concepts covered:
- How connectors function: OAuth authentication, permissions, and the scope of access granted.
- Managing tool access: enabling, disabling, and controlling which connectors Claude can use per conversation.
- Security awareness: connecting only to trusted services and reviewing tool permissions.
- The MCP ecosystem: where to find new connectors, extensions, and community-built servers.
Objective: Participants view Claude as a connective layer between all the services they already use, not just as a coding tool.
Break — 10 minutes
Phase 6 — Capstone & Next Steps — 65 minutes
Capstone mini-project (45 min): Each participant chooses one scenario and builds it with Claude:
- A polished landing page or portfolio site for their team, project, or personal brand.
- A data analysis pipeline: upload a file, have Claude analyze it, and produce a visual report.
- An interactive tool that solves a real problem from their workflow (calculator, tracker, converter, quiz).
- A connected workflow: pull data from a connected service, transform it, and produce a deliverable (e.g., “read my calendar for next week and build a visual schedule.”)
The instructor circulates to help refine prompts and showcases standout examples to the group.
Showcase and wrap-up (20 min):
- 6-8 participants share what they built (2-3 minutes each).
- Where to go from here: Claude Code CLI for terminal users, VS Code extension for developers, Cowork for knowledge workers.
- The MCP ecosystem: finding and evaluating new connectors, extensions, and community servers.
- Subscription plans: Free vs. Pro vs. Max — what each unlocks and which fits which use case.
- Best practices recap: the Prompt Playbook patterns that worked best 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 a curated list of useful MCP integrations.
Requirements
Prerequisites
Required Knowledge
- Basic computer proficiency: navigating files and folders, using web browsers, and installing software
- Familiarity with AI assistants (e.g., casual use of ChatGPT, Gemini, or Claude provides helpful context but is not mandatory)
Experience Level
- No coding, programming, or terminal experience is required. This course is specifically designed for individuals who have never written code.
- No prior familiarity with Claude or any other AI tool is necessary.
Technical Specifications
- Participants must bring a laptop (Mac, Windows, or Linux) equipped with a modern web browser.
- A stable internet connection is required.
- A Claude Pro subscription is needed for the session. A 1-month gift subscription is included with registration; setup instructions will be provided prior to the class.
- Claude Desktop is recommended but optional (the web app at claude.ai supports all exercises).
- A Google account is recommended for the MCP connectors exercise (Gmail, Google Drive, Google Calendar), though alternative connector options are available.
Target Audience
- Business professionals seeking to leverage AI for productivity and automation.
- Marketers, operations managers, and analysts aiming to automate repetitive tasks.
- Founders and entrepreneurs looking to build prototypes without hiring a developer.
- Educators and researchers exploring AI-assisted workflows.
- Anyone curious about Claude’s capabilities who lacks 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
