Meet Claude

Learning objectives

By the end of this lesson you'll be able to:

• Explain what Claude is and the principles that guide its design
• Describe Claude's core capabilities and how it differs from a simple chatbot
• Identify the different ways to access Claude (web, desktop, and mobile)

What is Claude?

Claude is more than a chatbot—it's an AI assistant designed to be your thinking partner.

Key takeaways

• Claude is built to be helpful, harmless, and honest: At a high level, Claude is guided by principles that help it avoid toxic or discriminatory outputs, avoid helping humans engage in illegal or unethical activities, and broadly behave as a helpful, honest, and harmless AI system. This approach, called Constitutional AI, means Claude is trained to align with human values and operate transparently.
• Claude is more than a chatbot: Claude is capable of a wide variety of conversational and text processing tasks while maintaining a high degree of reliability and predictability, including summarization, search, creative and collaborative writing, Q&A, coding, and more. Think of Claude as a thought partner who can help you tackle complex problems, and work through challenging situations, not just answer simple questions.
• Claude is designed to be steerable and collaborative: Claude can take direction on personality, tone, and behavior, and customers report that Claude is much less likely to produce harmful outputs, easier to converse with, and more steerable—so you can get your desired output with less effort.
• You can access Claude wherever you work: Claude apps are available to all plan types—Free, Pro, Max, Team, and Enterprise. Your conversations, projects, memory, and preferences sync across all devices when you're signed in. Whether you're at your desk or on the go, Claude is available through web, desktop, and mobile apps.

Understanding Claude's capabilities

Claude can help with a wide range of tasks that go far beyond simple question-and-answer interactions to assistant-like partnership that can both automate and augment your work. Here's a few things Claude excels at:

• Writing and content creation: Claude can collaborate with you on social media posts, professional emails, and complex reports. Because Claude is trained to take direction on personality and tone, you can iterate together on structure and clarity until your voice comes through clearly.
• Research and analysis: Claude helps you explore research angles, compile findings, and analyze data to surface meaningful insights. You can upload documents and Claude will help you make sense of complex information—this is enabled by Claude's large context window, which can ingest 200K+ tokens (about 500 pages of text or more), with up to 1M tokens available on Pro, Max, Team, and Enterprise plans when using Opus 4.7. This allows Claude to consider extensive materials in a single conversation.
• Coding assistance: Claude Opus 4.7 is our most powerful model yet and the best coding model in the world. This strong performance on real-world coding tasks means Claude can help you write, debug, and explain code across multiple programming languages.
• Problem-solving and reasoning: Claude handles complex cognitive tasks, mathematical problems, strategic thinking and analysis, and research. Claude Opus 4.7 and Sonnet 4.7 are hybrid models offering two modes: near-instant responses and extended thinking for deeper reasoning. Anthropic Extended thinking allows Claude to work through problems step-by-step, making it well-suited for tasks that require careful analysis.
• Learning new things: Whether you're learning a new skill, exploring unfamiliar domains, or working through complex challenges, Claude can adapt to your learning style and pace. Learning mode is a new Claude experience that guides your reasoning process rather than providing answers, helping develop critical thinking skills.

Your first conversation with Claude

Learning objectives

By the end of this lesson you'll be able to:

• Explain what Claude is and the principles that guide its design
• Describe Claude's core capabilities and how it differs from a simple chatbot
• Identify the different ways to access Claude (web, desktop, and mobile)

Key takeaways

• Claude is a powerful, intelligent collaborator that amplifies your capabilities across all of your work. Claude brings AI intelligence, but you bring the context and expertise that makes the work meaningful.
• The best approach when speaking to Claude is like you would a coworker—naturally, concisely, and conversationally.
• Before your next conversation with Claude, consider: setting the stage (your role, objectives, and context), defining the task (what action you want Claude to take), and specifying rules (style, tone, and examples).
• When you upload relevant documents or background information into a chat, Claude considers that content in its response—think of it as a shortcut so Claude can understand what your needs are.
• The real power of Claude comes with continued and frequent communication, not just one-off prompts.

Writing effective prompts

All interactions with Claude begin with a prompt, and these prompts, combined with other context, impact Claude's response. The best approach when speaking to Claude is like you would a coworker—naturally, concisely, and conversationally.

But you may ask, what is a good prompt? Before your next conversation with Claude, consider a few things:

1. Setting the stage: What is your role and what are your objectives? Is there context about your work that Claude should know about?
2. Defining the task: What action do you want Claude to take? Do you want Claude to write, analyze, build, or something else?
3. Specifying rules: What's the style or tone you want Claude to use? Are there examples that you can attach to show Claude what you're looking for?

Putting it together

Here's an example prompt that uses all three elements:

"I'm the marketing lead at an indie streaming startup, and we're preparing an investor pitch deck for Series A investors. Can you research the current state of the independent film streaming market and identify key trends, competitor positioning, and growth opportunities? Use current web research with citations and structure it as a professional report of up to 5 pages, with an executive summary, market analysis, competitive landscape, and growth opportunities."

In this prompt:

• Setting the stage: We tell Claude this is for an investor pitch deck for a new indie streaming app—that's the context and objective.
• Defining the task: We provide the specific action (research the market) with relevant details (trends, competitors, opportunities).
• Specifying rules: We ask for current web research with citations, structured as a professional report—telling Claude exactly what style and format we need.

Adding context

Uploads, connectors, and custom preferences offer ways to give Claude even more context about your work.

Claude can analyze both text and visual elements (like images, charts, and graphics) in PDFs and other documents. Supported file types include PDF, DOCX, CSV, TXT, and common image formats like PNG and JPEG.

Some practical ways to use file uploads:

• Upload a document and ask Claude to summarize the key points
• Share an image and ask Claude to describe or analyze what it sees
• Attach a spreadsheet and ask Claude to identify trends in the data
• Upload code and ask Claude to explain how it works or find bugs

Once uploaded, Claude will automatically attempt to parse the file's content. In the chat, the file appears as an attachment and you can then prompt Claude about it.

Pro-tip: If you'd like Claude to consider specific preferences in every response, go to Settings > General > 'What personal preferences should Claude consider?' to set preferences that apply to every conversation.

Iterating on Claude's responses

Conversations with Claude are meant to be iterative. Chaining bite-sized prompts together allows for a natural dialogue where you guide the conversation based on Claude's replies.

If Claude's first response isn't quite what you wanted, you have several options:

Ask follow-up questions: Build on Claude's response by asking for more detail, a different angle, or clarification. For example: "Can you expand on the second point?" or "That's helpful, but can you make it more concise?"

Provide feedback: Tell Claude what you liked and didn't like about its response. "This is good, but the tone is too formal. Can you make it more conversational?"

Redirect or restart: If Claude went in a different direction than you intended, simply steer it back. "Actually, I was asking about X, not Y. Let me clarify...". Worst case, restart your conversation in a new chat to fully refresh the context.

Pro tip: You can also click the pencil icon on any of your messages to edit and resubmit your prompt — useful when you want to refine your request rather than add a new message.

Personalizing Claude

There are two features that help Claude work better for you over time to increase the power of your prompts.

Memory automatically saves key context from your conversations — your role, preferences, past decisions, and working style — so you don't have to repeat yourself every time you start a new chat. For example, if you tell Claude you work in marketing at a B2B company, it'll remember that context going forward. You can review, edit, or delete anything Claude remembers anytime in Settings, and memory syncs across all your devices.

Styles let you customize how Claude communicates. Choose from preset options — like concise, formal, or explanatory — or create your own custom style by describing exactly how you want Claude to write. Once set, your style applies across all conversations automatically.

Getting better results

Learning objectives

By the end of this lesson, you will be able to:

• Recognize common challenges when starting out with AI and use troubleshooting techniques to overcome them
• Define AI Fluency and know where to go to learn more about working with AI in a fluent way
• Explain how you might set up evals to better understand how Claude might perform with your unique workflows

Common challenges and how to fix them

The iteration mindset

One of the most important shifts when working with Claude is recognizing that your first prompt rarely produces a perfect result—and that's okay. Think of your initial prompt as the start of a conversation, not a one-shot request.

Effective Claude users:

• Treat first drafts as starting points. Review what Claude produces, identify what's working and what isn't, then refine.
• Give specific feedback. "Make it shorter" is fine, but "Cut the first two paragraphs and make the conclusion more action-oriented" is better.
• Know when to start fresh. If a conversation has gone off track, sometimes it's faster to open a new chat with a clearer prompt than to try to redirect.

What is AI Fluency?

AI Fluency is the ability to collaborate effectively with AI tools—not just knowing which buttons to click, but developing the judgment to use AI well across different situations.

The 4D Framework for AI Fluency, developed through research collaboration between Professor Rick Dakan (Ringling College of Art and Design) and Professor Joseph Feller (University College Cork), identifies four core competencies that, when combined, can help you make the most of your AI interactions:

• Delegation: Deciding on what work should be done by humans, what work should be done by AI, and how to distribute tasks between them. Includes understanding your goals, AI capabilities, and making strategic choices about collaboration.
• Description: Effectively communicating with AI systems. Includes clearly defining outputs, guiding AI processes, and specifying desired AI behaviors and interactions.
• Discernment: Thoughtfully and critically evaluating AI outputs, processes, behaviors and interactions. Includes assessing quality, accuracy, appropriateness, and determining areas for improvement.
• Diligence: Using AI responsibly and ethically. Includes making thoughtful choices about AI systems and interactions, maintaining transparency, and taking accountability for AI-assisted work.

You've already been practicing these skills throughout this course. The prompt framework from Lesson 2 (setting the stage, defining the task, specifying rules) is rooted in Description. The troubleshooting techniques above draw on Discernment and Diligence.

To learn more, check out our free AI Fluency course that explore all four competencies in depth, with practical exercises and real-world applications.

Evaluating Claude for your workflows

As you start integrating Claude into more of your work, you might wonder: how do I know if Claude is actually good at this particular task?

This is where Discernment becomes essential. Evals (short for evaluations) are a way to develop intuition for assessing Claude's outputs on the tasks that matter to you. They're systematic ways to test how well Claude performs on specific types of tasks that matter to you.

Why evals matter

Your work is unique. Claude might excel at drafting marketing copy but need more guidance for technical documentation in your specific domain. Running simple evals helps you:

• Understand where Claude adds the most value in your workflow
• Identify tasks where you'll need to provide more context or examples
• Build confidence in Claude's outputs for recurring tasks

A simple eval approach

You don't need complex infrastructure to evaluate Claude. Here's a practical approach:

1. Gather examples. Collect 5-10 examples of a task you do regularly—emails you've written, reports you've created, analyses you've done.
2. Create test prompts. Write prompts that would generate similar outputs. Include the context you'd naturally have when doing this work.
3. Compare outputs. Run your prompts and compare Claude's responses to your examples. Ask yourself:
   • Does Claude capture the key information?
   • Is the tone and style appropriate?
   • What's missing or could be improved?
4. Refine your approach. Based on what you learn, adjust your prompts, add examples to show Claude what good looks like, or identify where human review is essential.

Claude desktop app: Chat, Cowork, Code

Learning objectives

By the end of this lesson you'll be able to:

• Identify the three modes in the Claude desktop app — Chat, Cowork, and Code — and what each is designed for
• Explain key features unique to each mode, including quick entry, scheduled tasks, and local vs. remote development
• Choose the right mode based on the type of work you need to accomplish

Navigating the Claude desktop app: Chat, Cowork, Code

The Claude desktop app gives you three ways to work with Claude: Chat, Cowork, and Code — from quick questions to complex research to building software.

Chat is the same Claude you know from claude.ai, plus quick entry, screenshots, dictation, and connectors that come from running natively on your computer. Cowork is an agentic tool — you give it a goal, connect it to your tools and resources, and let it do the work. With Cowork, Claude has the reach and the room to do more. This broader scope allows it to conduct more thorough research and analysis, and produce more complex documents and deliverables. Code is for building software, from writing and testing code to deploying it.

Cowork and Code run on the same engine. Both are Claude Code underneath — local to your machine, capable of independent work, able to spin up sub-agents and sustain long tasks. This allows Claude to work through larger tasks on its own, like research and writing or building software.

Each mode is designed around the work it serves, showing you what matters and giving you control where you need it.

Chat

Chat excels when you need to ask questions, brainstorm, draft, or work through problems back and forth.

If you've used claude.ai, this works the same way, with a few things that come from running natively on your computer:

• Quick entry. Double-tap the Option key on Mac to pull up Claude over whatever you're working on. It responds in a compact window that stays on top as you switch between apps. You never have to leave what you're doing to ask a question.
• Screenshots and window sharing. Capture a screenshot or share a window so Claude sees exactly what you're looking at. Faster than describing what's on your screen, and more precise. (Mac)
• Dictation. Talk through a problem instead of typing. Useful when you're thinking out loud, away from your keyboard, or working through something where speaking is faster than writing. (Mac)
• Desktop connectors. Connect local tools and services through connectors so Claude can work with other tools on your machine.

Try it out when:

• You're staring at an unfamiliar dashboard. Double-tap Option, drag your cursor over the window to screenshot it, and ask “what do these metrics mean?” Claude answers in the overlay while the dashboard stays in view.
• You're in between meetings and want to think through how to structure a presentation. Open quick entry, switch to voice, and talk it through. Claude drafts an outline from what you said.
• You've been jotting down ideas for a product launch across Apple Notes for weeks. You add the Notes connector from Settings and ask Claude: “Pull together everything in my notes about the Osprey launch, figure out where I left things half-finished, and check my other connected tools for anything that fills in the gaps.” Claude reads your notes on your machine, pieces together what you have, and follows up where you trailed off.

Cowork

Claude Cowork is built for work that takes real effort: pulling information from many sources, making sense of it, and producing something finished.

In Cowork, Claude can multitask, tackling different parts of a project at a time, so it has the scope to draw from more sources and the stamina to see things through. Thorough research briefs, cross-source financial analysis, end-to-end contract review, polished slide decks from material spread across sources.

Before starting, Claude often asks a short set of questions to pin down what you need: scope, format, constraints. It builds a plan you can review in the sidebar. As it works, you see the task come together: sources it's drawing from, files taking shape, progress through the plan. You can run multiple tasks at once, each in its own conversation, and switch between them from the sidebar.

• Folder access. Point Claude to a folder on your computer and it reads what's there, figures out what's relevant, and saves finished work back to the same place. You can also upload files, paste content into the conversation, or connect tools that pull in what Claude needs.
• Scheduled tasks. Claude can handle recurring work on a schedule: a daily briefing that pulls from your Slack and calendar, a weekly roundup of what shipped, a morning inbox triage that sorts what needs your attention. You define the task and when it should run, and Claude handles it automatically each time the app is open. If your computer or the app was closed when a task was due, it catches up when you're back.
• Subagents. Background workers that Claude spins up to handle parts of a task in parallel. If you ask for something complex — like a research brief that pulls from multiple sources — Claude breaks it into subtasks, assigns each to a subagent with its own context, and coordinates the results, giving you one finished deliverable.
• Dispatch. A persistent conversation thread that allows you to continue your Cowork conversations from your phone. From the Claude mobile app, you can hand Claude tasks that use everything on your computer — your files, connectors, plugins, even desktop apps. To use this feature, you need both the desktop and mobile apps, with your computer awake and the desktop app open.
• Projects. Projects in Cowork let you group related tasks into dedicated workspaces with their own files, context, instructions, and memory. If you use projects on Claude, Cowork projects work similarly, but they live locally on your desktop and are built around the tasks you run through Cowork.
• Browser use. Connect Claude in Chrome and Claude can navigate websites, interact with pages, and pull what it finds directly into the task it's working on. This is how Cowork does things like check competitor pricing across ten sites or gather data from pages that don't have an API.
• Computer use. When Claude doesn't have a connector or plugin for what you need, it can navigate your computer directly — clicking, typing, and opening apps just like you would. Claude follows a priority order: connectors first, then Chrome, then screen interaction, so it always picks the fastest, most reliable path. You'll see a permission prompt before Claude accesses each app, and you can set up a blocklist for anything you want off-limits. Computer use is in research preview on Pro and Max plans, macOS only (Windows coming soon)
• Plugins. Plugins give Claude capabilities it doesn't have on its own: pulling live financial data, searching your company's internal knowledge base, or working within a specific compliance framework. Browse and add them from the Cowork interface to fit the task.
• Protected environment. Cowork runs in a contained space on your computer. Claude can read, create, and edit files within the folders you share, but can't access anything outside them.

Try it out when:

• You want to query all your tools like you would a database. Ask “review what we decided about pricing last quarter across meeting notes, Slack, and email, then update our Q3 deck with the findings?” and Cowork finds the answer across meeting notes, slide decks, email, and Slack threads.
• You're researching a new market, scoping competitors, evaluating tools. For any research that might span multiple tabs with hard to extract information, Cowork visits the sites, reads the reports, pulls the pricing, and delivers a structured brief with sources, without you opening a single browser tab.
• You need to work through a folder of 50+ project documents including contracts, financial reports, and meeting transcripts. You can ask Cowork to find the documents most relevant to your initiative, and produce a summary memo. Cowork reads every page, cross-references across the full set, and pulls out the patterns that only emerge from reading all of them. Review fifty like you'd review five.
• You keep doing the same work every morning — checking messages, pulling together a status update, prepping for the day's meetings. Set it up once as a scheduled task and Claude handles it on repeat, so you start the day with answers instead of admin.

Code

The Code tab gives you access to the power of Claude Code, running directly inside the desktop app. This gives you a full development environment for building software.

Via Code, Claude works directly in your codebase: reading what's there, writing and modifying code, running commands. Visual diffs show what changed, a built-in terminal shows commands as they run, and git tracks every version so you can always roll back.

Where Cowork runs in a contained workspace limited to the folders you share, Code runs directly in your project with full access to your file system, terminal, and development tools.

You choose where work happens:

• Local: You select a folder on your computer and Claude works directly with those files. Because it runs on your machine, Claude can read your project, access local tools, and run a development server you can preview in your browser.
• Remote: You connect a GitHub repository and Claude works in a cloud environment. Sessions continue even if you close the app, so you can start a big refactor and check back later. Good for larger codebases or when you want to keep development off your local machine.

Three interaction modes let you control how much Claude does on its own:

• Ask: Claude proposes every change and waits for your approval. You review a visual diff and accept or reject before anything is modified.
• Code: Claude applies file changes automatically but checks before running terminal commands.
• Plan: Claude outlines its full approach before touching anything. A dedicated plan viewer lets you review and revisit the strategy as work progresses.

You can run multiple sessions across projects and filter them by status (Active or Archived) and environment (Local or Cloud) from the sidebar.

The Code tab is available on Pro, Max, Team, and Enterprise users.

Comparing the three modes