Video: Getting started with Claude.ai
Getting started with Claude.ai
Imagine this: you're looking at a blank page, wrestling with a big, complex project, and not sure where to start. What if you had a partner who could help you break it down? 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.
Let's explore chatting with Claude, beginning with the sidebar. Here you will encounter icons for creating new chats and jumping back into old ones. There are options for projects where you can organize your conversations with persistent context and custom instructions, and then artifacts which allow you to turn ideas into shareable apps, tools, or content. No matter what you hope to accomplish, Claude offers support to achieve your goals.
All interactions with Claude begin with a prompt, and these prompts, combined with other context, impact its response. The best approach when speaking to Claude is like you would a coworker: naturally, concisely, and conversational. But you may ask, what is a good prompt?
Before your next conversation with Claude, consider a few things. One, setting the stage. What is your role and what are your objectives? Is there context about your work that Claude should know about? Two, defining the task. What action do you want Claude to take? Do you want Claude to write, analyze, build, etc.? Three, specifying rules. Is there a style or tone you want Claude to use? Are there examples that you can attach to show Claude?
Let's review this prompt below. First, we're setting the stage by telling Claude this is for an investor pitch deck for a new indie streaming app. That's the context and the objective. Then, we define the task clearly by providing relevant details. Finally, we specify the rules by using current web research with citations, structuring it as a professional report, which tells Claude exactly what style and format we need. Perfect.
With your basic prompt in place, now comes the real power move: adding your specific context to make Claude's response truly tailored to your needs. When you upload relevant documents or background information into a specific chat, Claude considers that context in its response, whether that's company documents, project files, or background research. Think of it as a shortcut so that Claude can understand what your needs are. Claude can intake and output many file types such as PDF, CSV, docs, and more.
In the search and tools menu, you can level up your experience yet again by giving Claude access to more tools, to pull in more context, and it will pull in these tools as needed while solving your request. You might toggle on options like web search to let Claude research current market data, or use connected data sources to pull from Google Drive, allowing access to real-time information. Claude will choose the right approach.
While those options directly impact the information Claude has access to, there are a few more ways to customize how Claude responds. You could choose the best Claude model for your task. To use the model selector, start chatting with Claude or open an existing chat. The selected model will appear under your text input. To change it, click on the model name and choose which model of Claude you'd like to chat with instead. Changing the model will result in a new chat.
Claude currently supports numerous models with distinct capabilities intended to meet specific user's needs. Use the Claude Opus model for your most complex tasks. It's the largest scale model with hybrid reasoning capabilities, for example, running a multi-step financial analysis. Claude Sonnet is the best choice for everyday users and is our recommended default model. It balances sophisticated capabilities with cost effectiveness. Think of it like choosing the right tool for the job. You can always switch models based on what you're trying to accomplish.
Extended thinking mode is particularly valuable for complex thinking and analysis, though it increases latency and may not be necessary for simple questions and everyday conversations. To get the fastest output for more straightforward tasks, you can start with Sonnet models and leave thinking mode off. If you need more support, you can change the model or turn on thinking mode.
Claude Sonnet enables Claude to conduct systematic multi-angle investigations by automatically breaking down complex questions and exploring hundreds of sources to deliver comprehensive, cited reports in five to 45 minutes. Claude does the research for you while you focus on other high-value work.
Now just wait as Claude delivers to you a well-crafted response that effectively accomplishes your task. But the real power of Claude comes with continued and frequent communication, not just one-off prompts. The more you interact with Claude, the better it becomes at understanding your communication style and preferences for future conversations.
Working with Claude, you have a great partner and a powerful intelligent collaborator that amplifies your capabilities across everything you work on. Claude brings AI intelligence to your work. You bring the context and expertise that makes the work meaningful.
This video was published in December 2025. The "Use style" menu it shows has since been deprecated.
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.
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:
- Setting the stage: What is your role and what are your objectives? Is there context about your work that Claude should know about?
- Defining the task: What action do you want Claude to take? Do you want Claude to write, analyze, build, or something else?
- 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.
Want to go deeper? This prompt framework is adapted from 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). The framework identifies four core competencies—Delegation, Description, Discernment, and Diligence—that enable effective collaboration with AI.
Take our free AI Fluency course(opens in new tab) to learn how all four competencies work together to enable efficient, effective, ethical, and safe AI use.
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.
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.
Skills are reusable sets of instructions that teach Claude how to approach specific tasks and workflows. They can encode your preferences for everything from how you write and the output formats you want to the specific processes you follow, the expertise you want applied, or how you like different types of work handled. Claude applies them automatically whenever they're relevant. Lesson 7, Working with skills, shows you how to enable and create them; for a quick overview, visit the Anthropic Help Center(opens in new tab).
Put it into practice
Before moving on, try prompting Claude with a question or task. If you need an idea to get started, feel free to explore our use-case gallery(opens in new tab).
What's next
In the next lesson, we'll explore how to give Claude direction—adjusting its tone, format, and approach to match exactly what you need.