Claude Code for Non-Developers Training Course

Phase 1 — Introduction to Claude Code — 55 minutes

• Overview of Claude and the distinctions of Claude Code compared to standard chat interfaces
• The Claude product suite: claude.ai, Claude Desktop, Claude Code (CLI), and their interrelationships
• Interface walkthrough: navigating the Claude app, initiating coding sessions, and understanding the workspace
• The Claude Code reasoning process: the describe → plan → act → review cycle
• Permission management: understanding why Claude seeks confirmation before creating files or executing code
• Initial build: instructing Claude to generate a simple styled webpage from a single-sentence description
• Refining outputs: directing changes such as enlarging the header, altering color schemes, or adding navigation bars
• Guided exercise: Learners launch the Claude app, initiate a Claude Code session, and construct a personalized “About Me” webpage by describing their needs in plain English. They then practice refining the result through follow-up instructions.

Objective: Ensure all learners are comfortable with the interface and have overcome initial interaction barriers.

Break — 10 minutes

Phase 2 — Creating Functional Applications with Plain English — 70 minutes

This constitutes the core morning session. Learners complete four tasks of increasing complexity 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 such as using a dark theme, adding a sidebar, or ensuring responsiveness.
• Task 2 — Data Analysis: Provide Claude with a sample CSV file and request data summarization, trend identification, extraction of extreme values, and chart generation. This demonstrates how Claude writes and executes code on the user's behalf.
• Task 3 — Document Generation: Request Claude to read a data file and produce a formatted report, such as a sales summary, project status update, or meeting recap. This illustrates how Claude transforms raw data into polished deliverables.
• Task 4 — Automation Utility: Ask Claude to build a simple utility like a unit converter, quiz application, or budget calculator. This introduces the capability of creating interactive tools beyond static pages.

Following each task, the instructor explains the behind-the-scenes actions: which files were created, what code was written, and how to interpret the output. Learners record their most effective prompts in a shared Prompt Playbook.

Break — 10 minutes

Phase 3 — Optimizing Claude Code Usage — 50 minutes

• Prompting best practices: contrasting specific versus vague instructions
• Live demonstration: side-by-side comparison of weak and strong prompts for the same task
• Iteration and refinement: requesting explanations of choices, undoing changes, or trying 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 create complex outputs (e.g., analyzing data first, then building a dashboard from the results)
• Cost and usage management: understanding tokens, context windows, and subscription tiers
• Distinguishing when to use Claude Code versus standard Claude chat
• Guided exercise: Learners select a Phase 2 project and extend it with two new features using a multi-step prompt chain. They then compare their pre- and post-modification prompts to identify key differentiators.

Objective: Progress from “it works” to “I can consistently achieve high-quality results.”

Break — 10 minutes

Phase 4 — Custom Workflows: Live Build Session — 60 minutes

This phase shifts the group dynamic. Instead of individual practice, the cohort collaborates. The instructor facilitates while participants direct the process — citing real work challenges, suggesting prompt ideas, and debating trade-offs. The goal 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 X to output Y (e.g., meeting notes to action items; raw data to summary emails; customer feedback to themed reports)
• Draft — generating initial versions of documents typically written from scratch (e.g., proposals, emails, job descriptions, social media posts)
• Analyze — interrogating documents or datasets that lack time for detailed review (e.g., long reports, survey spreadsheets, contracts)

Setup and Context (10 min): The instructor introduces the archetypes and explains the session structure. Learners submit real workflow challenges from their roles via a shared document or chat.

Live Build #1 — Transform Workflow (20 min): The instructor selects a submitted problem and builds it live while the room contributes prompt ideas, objections, and refinements. The instructor narrates every decision. The session concludes with a reusable prompt template for the participant whose problem was addressed.

Live Build #2 — Draft or Analyze Workflow (20 min): Same format, utilizing a different archetype and a different participant’s problem.

Reflection and Sharing (10 min): Learners take a moment to note one surprising prompting tactic, one improvement they would make, and one pattern to retain. A brief group share follows, involving 3-4 volunteers. The instructor relates observations to the broader Prompt Playbook.

Phase 5 — Integrating Claude with Your Tools via MCP — 50 minutes

• Introduction to MCP (Model Context Protocol): the universal plug system for AI tools
• The significance of MCP: evolving Claude from a chat assistant into a connected workflow hub
• The Connectors Directory: browsing and adding integrations directly within the Claude app
• Desktop Extensions: one-click installations for Claude Desktop (eliminating the need for configuration files)

Live Demo: The instructor connects Claude to two services via the Connectors UI and demonstrates cross-tool workflows:

1. “Check my Google Calendar for tomorrow’s meetings and draft a preparation email for each”
2. “Read the latest updates from our project board and compose a status summary”
3. “Retrieve data from this connected service and generate a local report”

Guided Exercise: Learners 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 click, authenticate, and proceed
• Option B: Add a custom connector by pasting an MCP server URL (a test URL is provided by the instructor)
• Option C: Install a Desktop Extension from the marketplace (for Claude Desktop users)

Learners 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 addressed:

• Connector mechanics: OAuth authentication, permissions, and access scopes
• Tool access management: enabling, disabling, and controlling which connectors Claude uses per conversation
• Security awareness: connecting only to trusted services and reviewing tool permissions
• The MCP ecosystem: locating new connectors, extensions, and community-built servers

Objective: Learners perceive Claude as a connective layer between existing services, rather than just a coding tool.

Break — 10 minutes

Phase 6 — Capstone and Future Steps — 65 minutes

Capstone Mini-Project (45 min): Each learner selects one scenario to build with Claude:

1. A polished landing page or portfolio site for their team, project, or personal brand
2. A data analysis pipeline: uploading a file, having Claude analyze it, and producing a visual report
3. An interactive tool solving a real workflow problem (e.g., calculator, tracker, converter, quiz)
4. A connected workflow: retrieving data from a connected 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 standout examples to the group.

Showcase and Wrap-up (20 min):

• 6-8 learners share their projects (2-3 minutes each)
• Next steps: Claude Code CLI for terminal users, VS Code extension for developers, Cowork for knowledge workers
• The MCP ecosystem: discovering and evaluating new connectors, extensions, and community servers
• Subscription plans: Free vs. Pro vs. Max — features unlocked and suitability for different use cases
• Best practices summary: Prompt Playbook patterns that proved most effective during the session
• Recommended resources: official documentation, community channels, and Anthropic’s prompt engineering guide
• Learners receive a reference card detailing key prompting patterns, connector setup instructions, and a curated list of useful MCP integrations