Claude Code for Non-Developers Training Course

Phase 1 — Introduction to Claude Code — 55 minutes

• Understanding Claude and what distinguishes Claude Code from standard chat
• The Claude product family: claude.ai, Claude Desktop, Claude Code (CLI), and their interrelations
• Interface overview: navigating the Claude app, initiating a coding session, and understanding the workspace
• Claude Code’s thought process: the describe → plan → act → review cycle
• Understanding permissions: why Claude seeks approval before creating files or executing code
• Initial build: instructing Claude to create a simple styled webpage from a single-sentence description
• Iterating on results: refining elements such as header size, color scheme, and adding a navigation bar
• Guided exercise: Participants open the Claude app, initiate 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.

Objective: Ensure everyone is comfortable with the interface and has overcome the initial interaction barrier.

Break — 10 minutes

Phase 2 — Creating Real Projects with Plain English — 70 minutes

This is the core of the morning. Participants complete four progressively complex tasks using only natural language prompts.

• Task 1 — Interactive dashboard: Instruct Claude Code to build a styled dashboard displaying sample data with charts, stats, 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 request a data summary, trend identification, highest/lowest value detection, and visual chart generation. 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 illustrates how Claude transforms raw data into polished deliverables.
• Task 4 — Automation tool: Request Claude to build a simple utility — like a unit converter, quiz app, or budget calculator. This introduces the concept that Claude can build interactive tools, not just static pages.

Following each task, the instructor highlights Claude’s background actions: files created, code written, and how to interpret the output. Participants document their best prompts in a shared Prompt Playbook.

Break — 10 minutes

Phase 3 — Optimizing with Claude Code — 50 minutes

• The art of effective prompting: specific vs. vague instructions
• Live demonstration: side-by-side comparison of weak and strong prompts for the same task
• Iteration and refinement: asking Claude to explain choices, undo changes, or try alternative approaches
• Working with uploaded files: “read this document and summarize it,” “convert this spreadsheet into a chart”
• Multi-step workflows: chaining requests to build 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
• Distinguishing when to use Claude Code versus regular Claude chat
• Guided exercise: Participants select 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 differences.

Objective: Progress from “it works” to “I can consistently achieve excellent results.”

Break — 10 minutes

Phase 4 — Personal Claude Workflows: Live Build Session — 60 minutes

This phase shifts the energy of the room. Instead of solo practice, the group builds collectively. The instructor leads, but participants direct the process — naming real problems from their jobs, suggesting prompt ideas, and debating tradeoffs. The aim is to learn prompt judgment by observing a skilled individual navigate uncertainty in real time.

Three workflow archetypes structure the session:

• Transform — Take input X and produce output Y (e.g., meeting notes → action items; raw data → summary email; customer feedback → themed report)
• Draft — Generate a first version of content normally written from scratch (e.g., proposals, emails, job descriptions, social posts)
• Analyze — Interrogate documents or datasets that lack time for careful reading (e.g., 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 challenges from their jobs via a shared doc or chat.

Live build #1 — Transform workflow (20 min): The instructor selects one submitted problem and builds it live while the room suggests prompt ideas, pushbacks, and refinements. The instructor narrates every decision. The session concludes with a working prompt template that the originating participant retains.

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

Reflection & share-back (10 min): Participants take a moment to note one surprising prompting move, one area for improvement, and one pattern they are taking away. A brief group share follows — featuring 3-4 voices, not everyone. The instructor connects these observations to the broader Prompt Playbook.

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

• What is 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 (no configuration files required)

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

1. “Check my Google Calendar for tomorrow’s meetings and draft a prep email for each one”
2. “Read the latest updates from our project board and write a status summary”
3. “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 proceed
• Option B: Add a custom connector by pasting 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 — e.g., “Read my recent emails about project updates and create a summary document.”

Key concepts covered:

• Connector mechanics: OAuth authentication, permissions, and access grants
• Managing tool access: 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: Participants view Claude as a connective layer between all services they already use, not 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:

1. A polished landing page or portfolio site for their team, project, or personal brand
2. A data analysis pipeline: upload a file, have Claude analyze it, and produce a visual report
3. An interactive tool solving a real workflow problem (calculator, tracker, converter, quiz)
4. 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, assists with prompt refinement, and showcases standout examples to the group.

Showcase and wrap-up (20 min):

• 6-8 participants share their builds (2-3 minutes each)
• Next steps: 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 — what each unlocks and which suits which use case
• Best practices recap: 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