Claude is more than a chatbot—it's an AI assistant designed to be your thinking partner. In this lesson you'll learn what makes Claude different from other AI tools and see how it can help with a wide variety of work tasks.
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.
Ways to access Claude
Claude is the intelligence—the AI assistant you're learning to work with throughout this course. That same intelligence is available across multiple interfaces, each suited to different types of tasks.
Claude.ai (and the associated mobile and desktop apps) are the primary way most people interact with Claude. Here, you can ask questions, brainstorm ideas, create and edit documents, and a lot more. Claude.ai is ideal for conversations, writing assistance, research, analysis, and creating files. This is our focus in this course.
Claude Code is an agentic coding tool that is designed for developers but can be used for all kinds of file manipulation on your desktop. Claude Code can directly edit files, run commands, and create commits.
Claude and Slack brings Claude directly into your team's communication tool. You can chat with Claude in the AI assistant header from any channel or conversation, or by mentioning @Claude in threads. When you connect Slack to Claude, Claude searches your workspace's channels, direct messages, and shared files to find the context you need for better responses and research.
Claude for Excel lets you work directly with Claude in a sidebar in Microsoft Excel, where Claude can read, analyze, modify, and create new Excel workbooks. Claude for Excel is best for model analysis, assumption updates, error debugging, template population, formula explanations, and multi-tab navigation.
Starting your first conversation
When you open Claude.ai, you'll see a clean interface with a text input area at the bottom of the screen.
Your prompts can range from simple questions (like brainstorming code names for a new feature) to complex requests to co-create files.
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?
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.
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.
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.
What are Projects?
Projects are ideal for storing knowledge Claude should reference, organizing related chats around a specific topic or work area, and collaborating with team members who need access to the same shared context.
When to use Projects
Projects are particularly valuable when you're working on something ongoing—not just a one-off question. Consider creating a project when you have a workflow with:
Reference materials you'll use repeatedly (meeting notes, survey results, reports, historical data, etc.)
Consistent requirements for how Claude should respond (always use formal language, always cite sources, always follow our template)
Team collaboration needs where multiple people should work from the same foundation
Creating your first project
Setting up a project takes just a few minutes. Here's how to get started:
Step 1: Set up your project
1. Hover over the left sidebar and click "Projects," or navigate directly to claude.ai/projects
2. Click "+ New Project" in the upper right corner
3. Give your project a descriptive name (e.g., "Q4 Marketing Campaign" or "Product Documentation")
4. Add a brief description of what you're working on. While Claude doesn't see this description directly, it helps you and your teammates understand the project's purpose.
5. Choose your visibility settings: keep it private or share with your organization (for Claude for Work users)
Step 2: Add project instructions
Project instructions tell Claude how to behave across all conversations in this project. Click on "Instructions" to open the instructions panel.
Good project instructions typically include:
Context about what you're working on: "This project is for creating marketing content for our B2B software product."
Process instructions: "First consider a blog structure that will entice this audience, then write the draft."
Tone and style preferences: "Use a professional but conversational tone. Avoid jargon when possible."
Specific requirements: "Always include a call-to-action at the end of marketing copy."
Once you've written your instructions, click "Save instructions." These will apply to every chat in this project and work alongside any user preferences and styles you've set.
You can also use project instructions to automate workflows — for example, "When I upload a meeting transcript, create a structured summary using this template." Think of instructions as programming Claude's behavior for this project.
Step 3: Build your knowledge base
Your project's knowledge base is where you upload documents that Claude should reference. You'll find the files menu on the right side of your project's main page.
Click the "+" button to add content. You can upload various file types including PDF, DOCX, CSV, TXT, HTML, and more. You can also connect to Google Drive to link documents directly.
What to upload:
Reference documents (brand guidelines, style guides, templates)
Background materials (research reports, meeting notes, requirements docs)
Examples of work you want Claude to emulate
Technical documentation or specifications
Working within your project
Once your project is set up, you can start chatting with Claude. Each conversation within the project automatically has access to your knowledge base and follows your project instructions.
Collaboration features
For users on Claude for Work (Team and Enterprise) plans, projects become even more powerful through collaboration features.
Permission levels
When sharing a project, you can choose from three permission levels:
1. Can view: Members can see project contents, access knowledge, and chat—but can't make changes. Think of this as read-only access with discussion rights.
2. Can edit: Members have full collaboration power. They can modify instructions, update knowledge, manage other members, and actively contribute to the project.
3. Owner: Project creators control everything, including who sees the project. They can share with specific people or make projects visible to the entire organization.
Sharing your project
To share a project:
Open the project you want to share
Click the "Share project" button to the right of the project name
Add individual members using their name or email, or copy and paste a list of email addresses for bulk sharing (in this case, the project will show up in their "Shared with you" section)
Or, share with "Everyone at [your organization]" to make your project discoverable within the Team tab
Team members will receive email notifications when you share a project with them, and they can find shared projects in their "Shared with me" tab.
Best practices for projects
To get the most out of projects:
Start focused, then expand. Begin with a specific use case rather than trying to create one project for everything. You can always add more content as you go.
Keep your knowledge base current. Outdated documents can lead to outdated responses. Review and update your project knowledge periodically.
Write clear instructions. Be specific about what you want. Vague instructions lead to inconsistent results.
Name your documents descriptively. (e.g., 'Q4-2025-Sales-Report.pdf' not 'report.pdf') and group related files together. Claude uses filenames and proximity to understand relationships between documents.
Reference documents by name. When asking questions, you can mention specific documents to help Claude focus its search: "Based on our Q3 report, what were the top customer concerns?"
What are artifacts?
Artifacts are standalone, interactive outputs that Claude creates in a dedicated window alongside your conversation. Instead of getting a long block of code or text buried in the chat, you see your content rendered and ready to use—whether that's a working website, an interactive chart, or a document you can immediately download.
Claude automatically creates an artifact when content meets certain criteria:
It's significant and self-contained, typically over 15 lines
It's something you're likely to want to edit, iterate on, or reuse
It represents complex content that stands on its own without needing the surrounding conversation
It's content you'll want to reference or use later
Common artifact types
Claude can create different of artifacts, each suited to different needs:
Documents (including markdown, plain text, Word docs, PDFs, PowerPoint, and Excel): Great for anything text-heavy that you'll want to export or continue editing — like meeting notes, reports, project plans, blog posts, and other written content.
Code snippets: Working code in any programming language—Python, JavaScript, C++, and more. You can view the code, copy it, or download it to use in your own projects.
HTML pages: Complete web pages with HTML, CSS, and JavaScript in a single file. Perfect for landing pages, forms, interactive demos, or quick prototypes.
SVG images: Scalable vector graphics for logos, icons, illustrations, and other visual elements. These render directly in the artifact window so you can see exactly what you're getting.
Mermaid diagrams: Flowcharts, sequence diagrams, Gantt charts, org charts, and more. Describe the relationships you want to visualize, and Claude will create a diagram you can refine.
React components: Interactive UI elements with real functionality—calculators, dashboards, games, data visualizations. These aren't just mockups; they include actual logic and respond to user input.
Creating your first artifact
Creating an artifact is as simple as having a conversation. Just describe what you want, and Claude will determine whether to present it as an artifact.
For example, you might say:
"Create a flowchart showing our customer onboarding process (Note: Claude may now generate visual diagrams like flowcharts as HTML using Imagine, in addition to code-based artifacts.)"
"Build an interactive dashboard that lets me input monthly expenses and see a breakdown"
"Design a landing page for a productivity app with a hero section and feature list"
"Write a project brief template I can reuse for new initiatives"
If Claude doesn't automatically create an artifact when you expect one, you can explicitly ask: "Create this as an artifact" or "Show me this in an artifact."
When Claude generates an artifact, it appears in a dedicated window to the right of your conversation. From here, you can:
View different formats: Toggle between a preview (how it looks) and the underlying code
Copy content: Click the copy icon to grab the content for use elsewhere
Download files: Save the artifact as a file to your computer
View code: See exactly what Claude generated under the hood
Sharing and publishing artifacts
Once you've created something useful, you have several options for sharing it.
Copy or download: For personal use or sharing via other channels, use the copy or download buttons in the lower right corner of the artifact window.
Share within your organization (Claude for Work): Team and Enterprise users can share artifacts internally with colleagues. The shared artifact stays within your organization and requires team authentication to access.
Publish publicly: For free, Pro, and Max users, you can publish artifacts to make them accessible to anyone with the link. When you publish:
Only the selected version becomes public (your chat remains private)
Anyone can view and interact with the artifact without a Claude account
Others can "remix" your artifact—opening it in their own Claude conversation to modify and build upon it
To publish, click the "Share" or "Publish" button in the upper right corner of the artifact. You can unpublish at any time by returning to that artifact and removing public access. Note: When you publish an artifact, it is publicly accessible via its link — anyone can view it, even without a Claude account. Published artifacts are not indexed by search engines, so they won't appear in Google results.
What are Skills?
Skills are folders of instructions, scripts, and resources that Claude loads dynamically to improve performance on specialized tasks. Think of them as expertise packages—they teach Claude how to complete specific tasks in a repeatable way.
Enabling Skills
Skills are currently available as a feature preview for users on Pro, Max, Team, and Enterprise plans. To use Skills, you'll need to have Code execution and file creation enabled, since Skills require Claude's secure sandboxed computing environment to function.
Here's how to enable Skills:
1. Navigate to Settings > Capabilities
2. Ensure that Code execution and file creation is toggled on
3. Scroll to the Skills section
4. Toggle individual skills on or off as needed
For Enterprise plans, organization Owners must first enable both Code execution and Skills in Admin settings before individual members can access them.
For Team plans, this feature preview is enabled by default at the organization level.
Skills are procedural machines. They encode how Claude should execute a task—the specific steps, order of operations, and methodology you want followed every time. Skills shine when you have repeatable workflows you want Claude to run consistently.
What are connectors?
Key takeaways
Connectors transform Claude from an assistant into an informed collaborator by giving Claude access to the same tools, data, and context that you use every day. Instead of starting every conversation from scratch, Claude can work directly with your actual information.
Connectors allow Claude to read information and perform actions on your behalf. Depending on the connector and permissions you grant, Claude can search your files, retrieve documents, analyze data, create new content, update records, and execute tasks across your connected applications—all from within your conversation.
The Model Context Protocol (MCP) powers connectors. Think of MCP like USB-C for AI—a universal standard that allows Claude to connect to many different applications through a single, consistent interface. This open standard means developers can build connectors for any tool, and those connectors work seamlessly with Claude.
There are two types of connectors: web connectors and desktop extensions. Web connectors link Claude to cloud services like Google Drive, Notion, Slack, and Asana. Desktop extensions run locally on your computer through the Claude Desktop app, giving Claude access to local files and native applications.
Finding and connecting tools
Anthropic maintains a directory of recommended connectors at claude.ai/directory. The directory is organized into two tabs:
Web: Cloud services and applications (Gmail, Notion, Slack, Asana, Linear, Stripe, and many more)
Desktop extensions: Local tools that run on your computer through the Claude Desktop app
To browse available connectors, you can also click the + button in the lower left of the chat window, then select Connectors.
Setting up a web connector
Here's how to connect a cloud service:
1. Find the connector: Navigate to claude.ai/directory, or click + > Connectors in any chat
2. Click Connect: Select the connector you want to add
3. Authenticate: You'll be redirected to the service's login page. Sign in with your existing credentials
4. Grant permissions: Review the specific permissions Claude is requesting, then authorize access
5. Test the connection: Return to Claude and try a simple request, like "Can you access my [tool name]?"
Once connected, Claude can search, read, and in some cases take actions within that service—depending on the permissions you've granted.
Desktop extensions
Desktop extensions require the Claude Desktop app rather than the web interface. These extensions let Claude interact with local applications, your file system, and native features on macOS or Windows.
Some desktop extensions include:
Local file access for reading and organizing documents
Browser control for automated web tasks
Native application integration (like Figma for design work)
To install a desktop extension:
1. Download and install the Claude Desktop app
2. Open the app and navigate to Settings > Extensions
3. Browse available extensions and click Install
4. Follow any additional setup steps specific to that extension
Using connectors in your work
Once you've connected your tools, Claude considers them when responding to your requests. Here are some practical ways to use connected tools:
Project management (Asana, Linear, Jira)
"What are my highest priority tasks due this week?"
"Create a new task for reviewing the Q4 budget proposal"
"Summarize the status of our product launch project"
Communication (Slack, Gmail)
"Find the email thread where we discussed the vendor contract"
"Draft a reply to the latest message in the #marketing channel"
"What did the team decide about the timeline in yesterday's discussion?"
Documentation (Notion, Google Drive, Confluence)
"Search our documentation for our brand voice guidelines"
"Summarize the meeting notes from last week's product review"
"What does our style guide say about using contractions?"
Business tools (Stripe, PayPal, Salesforce)
"Show me revenue trends for the past quarter"
"What's the status of the Acme Corp opportunity?"
"List recent transactions over $1,000"
Security and permissions
When you connect Claude to external services, you're granting it access to read—and sometimes modify—data within those services. Here are some important considerations:
Scoped access: Permissions are specific to what the connector needs and you can toggle individual permissions on and off within each application's menu.
Claude sees what you see: Claude can only access data you have access to. Connecting your work email doesn't give Claude access to your CEO's inbox—only your own.
Revocable at any time: You can disconnect a service through Claude's settings or through the third-party service's security settings. Just as with Skills, you can also find or build custom connectors. Exercise the same caution — only install connectors from trusted sources.
What is Enterprise Search?
Enterprise Search adds a dedicated "Ask {Your Org Name}" option to your sidebar. This is designed specifically for finding and synthesizing knowledge buried across your company's tools and data sources. Think of Enterprise Search as a pre-built Project for your entire organization — your company's knowledge base is already loaded, so you can jump right in to get context-aware responses to your questions.
Unlike regular chats with connectors enabled, Enterprise Search is specifically designed for information gathering, using custom instructions configured by the Anthropic team.
What can you ask?
Enterprise Search is particularly valuable for questions that span multiple sources or require synthesizing information from across your organization. Here are some common use cases:
Getting up to speed
"What happened yesterday while I was out?"
"Summarize key updates across the business from the last week"
"What are the current blockers on the Platform project?"
Policy and process questions
"What is our company's remote work policy?"
"How do I submit an expense report?"
"What's the process for requesting time off?"
Research and analysis
"What are the main reasons customers cite for choosing competitors?"
"Summarize discussions about the Q4 product roadmap"
"Find information about our customer onboarding process"
Onboarding new team members
"How does our authentication system work?"
"Who should I talk to about learning the billing system?"
"What tools does the engineering team use for deployment?"
Performance and project tracking
"Find discussions and documents related to the marketing campaign"
"What were the key decisions from last week's leadership meetings?"
"Summarize team contributions to the Infrastructure initiative"
When you ask a question, Claude searches across all your connected tools—such as SharePoint documents, Slack conversations, Gmail threads, and Google Drive files—and synthesizes information into a unified response. Plus, it always cites its sources so you can get the full context.
Setting up Enterprise Search
Enterprise Search requires a two-step setup process: first an admin configures it for the organization, then individual users authenticate with their personal accounts.
For admins (Owners)
The Enterprise Search project is enabled by default for all Team and Enterprise organizations, but an Owner needs to complete the initial setup before team members can use it:
1. Click "Ask Your Org" in the left sidebar.
2. Click "Set up for your org" to continue (or "Disable" to turn the feature off).
3. Connect your organization's tools. You'll be required to choose a connector for Documents (like Google Drive or SharePoint) and Chat (like Slack or Microsoft Teams). Email is recommended but optional.
4. Click "+ Add more" to set up any additional tools your team needs.
5. Customize the project name. Whatever you enter will appear as "Ask [Name]" in everyone's sidebar.
6. Add a description, then click "Finish set up."
Once setup is complete, the project becomes available to all members of your organization.
For users
After an admin has set up Enterprise Search, you'll see the "Ask {Org Name}" project starred in your sidebar. Here's how to get started:
1. Click on the project in your sidebar.
2. Follow the guided onboarding flow to connect to the recommended services.
3. Authenticate with each service you want to search (Slack, Google, Microsoft 365, etc.).
4. Start asking Claude questions about your organization's knowledge.
The more connectors you enable, the more comprehensive your search results will be. You can always add more connectors later by clicking "Connect" in the project's Instructions section.
Researching with Claude
Research is an advanced feature that transforms Claude from a conversational assistant into a systematic investigator. When you enable Research, Claude doesn't just answer your question—it explores it from multiple angles, synthesizing information from across the web and your connected integrations.
Research is particularly valuable when you need more than a quick answer. It's designed for situations where a thorough understanding requires pulling together information from multiple sources, comparing different perspectives, and synthesizing findings into actionable insights.
When to use Research
Understanding when to use Research versus other Claude capabilities helps you get the best results for your specific needs.
Use Research when you need
Comprehensive reports that synthesize information from multiple sources
In-depth analysis across the web and your connected integrations (like Google Workspace)
Thorough investigations that would typically require hours of manual work
Comparative analysis, such as evaluating competitors or vendor options
Reports with citations you can verify
How Research works
When you enable Research, you're activating an agentic, multi-step process that goes far beyond a simple web search. Claude autonomously decides what to search next based on what it has already found, pursuing leads and filling gaps without you needing to direct each step.
1. Step 1: Claude plans its approach. When Research is enabled, extended thinking automatically activates. This lets Claude break down your request, identify what information it needs, and plan how to investigate different angles of your question.
2. Step 2: Claude conducts multiple searches. Rather than running a single search, Claude conducts many searches that build on each other. It determines what to investigate next based on what it finds, pursuing promising leads and filling in gaps.
3. Step 3: Claude synthesizes findings. After gathering information from multiple sources—including the web and any connected integrations like Gmail, Google Calendar, or Google Drive—Claude compiles everything into a comprehensive, well-organized report.
4. Step 4: Claude provides citations. Every claim in Research reports links back to its source, making it easy to verify information and dig deeper when needed.
Using Research in practice
Here's how to enable and use Research:
1. Click the + button on the bottom left of your chat interface
2. Select Research from the menu—it appears highlighted once active
3. Enter your prompt and submit
4. Claude will work in the background, and you'll see progress indicators as it searches and analyzes
Claude in action: use-cases by role
These use cases apply across many roles and industries.
• Generate project status reports – Keep stakeholders informed with clear, consistent updates
• Analyze patterns in user feedback – Extract insights from customer comments and survey responses
• Package your brand guidelines in a skill – Create a reusable Claude skill that applies your brand standards
Sales
Sales professionals can use Claude to accelerate deal preparation, create compelling materials, and stay on top of competitive intelligence.
• Build a battle card library – Create competitive intelligence resources that help your team win deals
• Prepare for sales deals – Research prospects and organize your talking points before important meetings
• Create sales reports – Turn your pipeline data into clear, actionable reports
Marketing
Marketers can leverage Claude to analyze performance data and efficiently repurpose content across channels.
• Analyze campaign performance – Extract insights from campaign metrics to inform your strategy
• Adapt content across platforms – Efficiently repurpose content for different channels and audiences
Finance
Finance professionals can use Claude to build models, draft documents, and make sense of complex spreadsheets.
• Build financial models – Create and refine financial projections with Claude's help
• Draft investment memos – Structure and write investment analyses more efficiently
• Understand and extend an inherited spreadsheet – Decode complex spreadsheets and add new functionality
HR
HR teams can use Claude to create better onboarding experiences and documentation.
• Create new hire onboarding guides – Develop comprehensive onboarding materials tailored to different roles
Legal
Legal professionals can use Claude to track complex timelines and manage discovery processes.
• Track discovery timelines and analyze patterns – Organize case timelines and identify key patterns in legal documents
Research
Researchers can use Claude to plan literature reviews and verify data analysis.
• Plan your literature review – Organize your approach to reviewing academic sources
• Verify statistics from raw data – Double-check calculations and statistical analyses