Skip to content
AnthropicAnthropic

Getting started with Claude.ai

Learn how to get the most out of chatting with Claude. This tutorial covers the basics of Claude's conversational interface, including how to craft effective prompts, upload supporting documents, use search and tools, customize your experience with styles and model selection, and leverage features like extended thinking and research mode. Whether you're new to Claude or looking to level up your skills, this video will help you work more effectively with your AI collaborator.

Dec 2, 20255mWatch on YouTube ↗

CHAPTERS

  1. Claude as a collaborative partner for complex work

    The video opens by framing Claude as a thought partner for starting and structuring big, complex projects. It emphasizes that Claude contributes AI capability while the user supplies the domain context that makes the output meaningful.

  2. Navigating the Claude.ai sidebar: chats, projects, and artifacts

    This chapter tours the core UI entry points in Claude.ai. It explains where to start new chats, return to prior conversations, organize work in Projects, and create shareable outputs via Artifacts.

  3. Prompts as the foundation: talk to Claude like a coworker

    The video explains that every interaction starts with a prompt and that prompt quality strongly shapes the response. It recommends a natural, concise, conversational style similar to communicating with a colleague.

  4. Prompt framework (1): Set the stage with roles, goals, and context

    The first part of the prompting framework focuses on establishing the situation. Viewers are encouraged to define their role, objectives, and any background information Claude should know.

  5. Prompt framework (2): Define the task and the action you want

    Next, the video stresses being explicit about what you want Claude to do. It highlights specifying the type of work—writing, analysis, building, and more—to steer the response toward the right deliverable.

  6. Prompt framework (3): Specify rules, style, and examples

    The third prompting element is setting rules for output format and tone. The video recommends specifying style requirements and attaching examples when available to align Claude’s response with expectations.

  7. Worked prompt example: investor pitch deck research report

    A concrete example ties the framework together: a prompt for an investor pitch deck for an indie streaming app. The example demonstrates context + clear task definition + rules like web research with citations and professional report structure.

  8. Tailoring outputs by adding your documents and background context

    The video explains the “power move” of uploading relevant materials into a chat so Claude can respond with deeper specificity. This helps Claude understand company, project, or research context without repeated explanation.

  9. File support: using common formats to power your workflow

    This chapter highlights that Claude can work with many file types, enabling broader real-world workflows. It mentions common formats used in business and analysis contexts.

  10. Search and tools: expanding Claude’s available context

    The video introduces the search and tools menu to enhance what Claude can access. By enabling tools like web search or connected data sources, Claude can incorporate more up-to-date or internal information when solving requests.

  11. Choosing the right Claude model for the job

    This chapter explains how to select a model and why model choice matters. It notes where the model selector appears, how switching models starts a new chat, and how models differ in capability and intended use.

  12. Model guidance: Opus for complexity, Sonnet for everyday work

    The video provides practical guidance on when to use specific models. Opus is positioned for the most complex, multi-step reasoning tasks, while Sonnet is recommended as an everyday default balancing capability and efficiency.

  13. Extended Thinking mode and Research: deeper analysis and cited reports

    This chapter distinguishes between quick responses and deeper reasoning workflows. It describes Extended Thinking for complex analysis (with added latency) and Research mode for systematic, multi-source investigations delivering cited reports over minutes to tens of minutes.

  14. Getting the most value: iterate frequently and build a working relationship

    The closing emphasizes that Claude works best through ongoing, iterative communication rather than one-off prompts. With continued interaction, Claude better matches your style and preferences, reinforcing the human+AI partnership theme.

Get more out of YouTube videos.

High quality summaries for YouTube videos. Accurate transcripts to search & find moments. Powered by ChatGPT & Claude AI.

Add to Chrome