Course Outline
Phase 1 — Introduction to Claude Code — 55 minutes
- Understanding Claude and what distinguishes Claude Code from standard chat interfaces
- Overview of the Claude product ecosystem: claude.ai, Claude Desktop, Claude Code (CLI), and their relationships
- Interface navigation: exploring the Claude app, initiating a coding session, and understanding the workspace
- Claude Code’s reasoning process: the describe → plan → act → review loop
- Understanding permissions: why Claude requests approval before creating files or executing code
- Your first build: instructing Claude to create a simple styled webpage based on a one-sentence description
- Iterating on results: refining designs with commands like “make the header larger,” “change the color scheme,” or “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 preferences in plain English. They practice refining results through follow-up instructions.
Goal: ensure everyone is comfortable with the interface and has overcome the initial learning curve.
|
Break — 10 minutes |
Phase 2 — Building Real Projects with Plain English — 70 minutes
This segment forms the core of the morning. Participants complete four increasingly complex tasks using only natural language prompts.
- Task 1 — Interactive dashboard: instruct Claude Code to build a styled dashboard displaying sample data with charts, statistics, and a clean layout. Practice providing design direction: “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, find highest and lowest values, and generate a visual chart. This demonstrates how Claude writes and executes code on your behalf.
- Task 3 — Document generator: ask 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: ask Claude to build a simple utility — such as 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 highlights 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 — Optimizing Workflows with Claude Code — 50 minutes
- The art of effective prompting: distinguishing between specific and vague instructions
- Live demo: side-by-side comparison of weak versus strong prompts for the same task
- Iterating and refining: asking Claude to explain its decisions, undo changes, or attempt alternative approaches
- Working with uploaded files: commands like “read this document and summarize it” or “convert this spreadsheet into a chart”
- Multi-step workflows: chaining requests to build complex outputs (e.g., “first analyze this data, then build a dashboard from the results”)
- Understanding cost and usage: how tokens, context windows, and subscription tiers function
- Knowing when to use Claude Code versus standard Claude chat
- Guided exercise: participants take one of their Phase 2 projects and extend it with two new features using a multi-step prompt chain. They then compare their before-and-after prompts to identify key differentiators.
Goal: 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 room’s energy. Instead of solo practice, the group builds together. The instructor drives the technical implementation, while participants dictate the direction — providing real-world problems from their jobs, suggesting prompt ideas, and debating tradeoffs. The objective is to learn prompt judgment by observing how an expert navigates 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 content you would normally 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 mechanics. Participants submit real workflow problems from their jobs via a shared document or chat.
Live build #1 — Transform workflow (20 min): The instructor selects one submitted problem and builds it live, with the room contributing prompt ideas, pushbacks, and refinements. The instructor narrates every decision. The session concludes with a working prompt template that the contributor keeps.
Live build #2 — Draft or Analyze workflow (20 min): Same format, but focusing on a different archetype and addressing a different participant’s problem.
Reflection & share-back (10 min): Participants take a moment to record one prompting move that surprised them, one thing they would do differently, and one pattern they will apply. 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 with MCP — 50 minutes
- What is MCP (Model Context Protocol)? The universal plug 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 required)
Live demo: The instructor connects Claude to two services via 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 varying 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 give Claude a task that utilizes the connected service — for example, “Read my recent emails about project updates and create a summary document.”
Key concepts covered:
- How connectors function: OAuth authentication, permissions, and the extent 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 discover new connectors, extensions, and community-built servers
Goal: participants view Claude as a connective layer between all their existing services, rather than just a coding tool.
|
Break — 10 minutes |
Phase 6 — Capstone & Next Steps — 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 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 workflow problem (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 their builds (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
- Plans: Free vs. Pro vs. Max — understanding what each unlocks and which fits specific use cases
- Best practices recap: reviewing the Prompt Playbook patterns that proved most effective 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 literacy: proficiency in 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 beneficial context, though not mandatory)
Experience Level
- No coding, programming, or terminal experience is required. This course is tailored for individuals who have never written code.
- No prior experience with Claude or other AI tools is necessary.
Technical Requirements
- Participants must bring a laptop (Mac, Windows, or Linux) equipped 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 will be sent prior to the class)
- Claude Desktop is recommended but optional (the web application at claude.ai 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 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
