Claude AI: The AI Assistant You’ll Actually Use

Welcome to the new video!

Covered in the video:

• What is a prompt, what do we mean by prompting, and how does prompt engineering tie it all together?

• The distinction between chat and enterprise prompting.

Hey everyone, welcome to our first lecture on chat prompting!

Here, you’ll learn how to approach creating and refining prompts that can be used in the Claude.ai chat interface as well as with other similar models.

Let’s get started!

Covered in the video:

• Prompting formula components: task, task context, tone, rules, role, and audience context.

If, after watching the previous lecture, you feel like creating a good prompt is an arduous task and that you need to turn into a prompt engineer to succeed in this job, here's a secret the experts use: think of prompting as a conversation or a multi-step process, not a one-time question.

Just like you might clarify directions in a new city with a local, you can refine your prompts based on Claude's responses.

Covered in the video:

• What is iterative prompting.

• Iterative prompting steps.

• Memory referencing prompting technique.

We're going to explore how to make Claude truly yours by using two powerful customization features: profile preferences and conversation styles.

Covered in the video:

• What are profile preferences and how to customize them.

• Claude conversation styles and their differences.

Hey everyone, welcome back!

Now that we’ve covered how to talk to Claude and what essential things to include in your prompt, let’s dive into our first practical activity.

For this activity, I’ll pretend that I’d like to start a side hustle project using my expertise in product management, and I’ll rely on Claude to assist me with the project idea brainstorming process.

You’ll see me iterating on my prompt by including additional details so that you can see how our output changes and becomes more refined. You’re welcome to follow along by brainstorming the exact same side hustle idea, or you can choose a brainstorming topic based on your own interests.

I hope you're ready—let’s get started!

Hey everyone, welcome back!

In this tutorial, I’ll show you a quick technique you can use to enhance your prompt, especially at the beginning of your experiments with Claude when you’re just learning prompting techniques.

In the previous lectures on prompt engineering with Claude, we talked a lot about how to frame your instructions and what information to include.

However, apart from the instructions themselves, oftentimes you may also need to submit certain documents that need reviewing and analysis.

Let’s see how it works.

Covered in the video:

• How to instruct Claude to work with your documents for the best result.

• How to work with multiple files.

Hey everyone, and welcome back to the new lecture where we continue talking about how to communicate with Claude and what to include in your prompt description.

Covered in the video:

• How to use examples in your prompts.

• Difference between one and few-shot examples.

• What are interactive examples and why do you need them?

Hey everyone! We are almost done covering the key ingredients of a good prompt.

There’s yet another component you may find worth including in your prompt—information on what format you want Claude’s response to take.

Let’s talk about this now.

Covered in the video:

• How to specify your formatting preferences in a prompt.

• Examples of formatting you can request from Claude.

Hey everyone, welcome to the new follow-along lecture.

Here, we are going to explore a use case I believe is one of Claude’s strongest.

We’ll create marketing materials, specifically a marketing email sequence, which will be used to spread the word about a new product among prospective customers and invite them to try its trial version.

This was the first scenario I used Claude for, and I was impressed by the quality of the results.

So, I decided that I definitely want to have Claude.ai among my generative AI tools.

Welcome to the second part of the follow-along lecture, where we explore using Claude to create marketing materials.

Welcome, everyone! In the first lecture of this section, we are going to talk about Claude's Artifacts—but don’t worry, no ancient pyramids here—just powerful tools to help organize and structure your conversations with Claude.

Covered in the video:

• What Artifacts are and why you need them in Claude.

• Example of creating and modifying an Artifact.

Welcome back!

In the previous tutorial, we created an artifact by describing what we needed directly in the chat. That works well, and you'll use it often. But there's a second way to create artifacts — a guided flow where Claude walks you through a set of questions before it builds anything. That's what we'll use now.

Covered in the video:

• Claude's step-by-step question flow before it builds anything.

• How to review the plan, confirm it, and refine the result through follow-up messages.

• How to share your artifact using Claude's publish link or host it on the web with Netlify Drop.

Welcome back!

We've covered what artifacts are — separate spaces where Claude creates content alongside your conversation. Now we're looking at a different kind of artifact.

Covered in the video:

• Understand how AI-powered artifacts differ from regular artifacts.

• Build an artifact where Claude responds fresh to every user input.

• Learn what triggers Claude to build AI into an artifact automatically.

• Refine the design and functionality through follow-up chat messages.

• Publish the tool so anyone with a Claude account can use it.

At the beginning of our course, we mentioned that we’d discuss how to optimize usage limits and get the most out of your subscription plan. This is where using Artifacts can be especially helpful.

Covered in the video:

• How Claude usage limits are measured.

• How to improve Claude’s performance with the help of Artifacts.

• Two additional recommendations for maximizing your usage limits (whether or not you are using Artifacts).

Hey everyone, welcome to the follow-along lecture!

Let’s practice creating artifacts!

In this tutorial, we’ll create a Process Flow for a New Employee Onboarding process. Just in case you're not familiar with what a process flow is: it's a visual representation of the sequence of steps, activities, and decisions required to complete a business process from start to finish.

As always, you’re welcome to follow along by creating the diagram for the exact same process, or you can choose a process relevant to your work area—customer complaint resolution workflow, sales lead qualification process, return/refund handling workflow—you name it!

So, let’s begin the demo.

Welcome to the second part of the tutorial on creating the Process Flow with Claude!

Now that you know what artifacts are, and how to create, modify, publish, and remix them, let’s learn about another useful feature of Claude—Projects—which can help you organize your work with Claude (available in the paid plans only).

Covered in the video:

• What projects are in Claude.

• How to create a project.

• How to work with a project's knowledge base.

• How to set custom project instructions.

• When you should create a project instead of a one-off conversation.

Hello and welcome to the new section of the course on Claude Skills!

Covered in the video:

• What Skills are.

• How they differ from Custom Instructions and Projects.

• Overview of what will be covered in the section.

In this tutorial, we're going to explore two types of skills in Claude.

Covered in the video:

• Understanding the difference between built-in skills and example skills.

• Creating professional Word documents using Claude's built-in docx skill with proper formatting and structure.

Welcome to the second part of the tutorial! Now let's create a different type of document - a PDF final report.

Covered in the video:

• Understanding the difference between artifact PDFs and skill-generated PDFs.

• Creating polished PDF reports with features like cover pages, headers, footers, page numbers, tables, and visual hierarchy.

Welcome back! Now let's switch gears and use a different type of skill - canvas-design.

Covered in the video:

• Understanding example skills like canvas-design.

• Creating visual designs like posters and graphics without specifying technical design details.

• How skills interpret design directions automatically.

Welcome back! In the next series of videos, we're going to explore one of Claude's most powerful features: custom skills.

Covered in the video:

• Understanding the three methods for creating custom skills.

• Creating a custom brand theme with your company colors, fonts, and design specifications by extending theme-factory skill.

Welcome to the new tutorial on Claude Skills! Now let’s explore the second option creating a custom skill - by writing skill instructions.

Covered in the video:

• Understanding when to create skills using written instructions.

• How to write effective skill instructions.

• Testing skills to compare default Claude responses versus skill-guided outputs.

So far, you've seen how to create both simple and complex skills. Now let's talk about when you should build a skill - and when you shouldn't.

Covered in the video:

• The two criteria for creating a skill.

• When NOT to build skills.

• Troubleshooting the three most common skill issues.

Let's look at something more advanced: creating complex skills. In this tutorial we are going to create a case-study presentation skill using our own assets - presentation templates and fonts.

Covered in the video:

• Understanding the three components of a Claude skill.

• Using the "Create with Claude" method to collaboratively build complex skills through conversation.

Welcome to the second part of the tutorial on creating complex skills with Claude.

Covered in the video:

• How to analyze existing designs and translate visual aesthetics into skill instructions that Claude can follow.

So far in this course, Claude has been answering you. You ask, it replies. You give it a Skill, it matches your style. You hand it a file, it reads and responds. Every time, Claude waits for you to make the next move.

That's about to change.

In this section, we meet Cowork. Cowork flips the whole relationship. You stop directing every step. You hand over the entire job. Then you walk away — and come back to finished work.

Covered in the video:

• The core shift from turn-by-turn chat to handing over an entire job.

• Why direct file and tool access is what makes autonomous work possible.

• A simple framework for knowing when to use Chat and when to use Cowork.

Welcome back! In this tutorial, we'll install the Claude Desktop app, where Cowork lives, and then we'll take a walk around the Cowork screen, so you know what each part does and where you'll actually start.

Covered in the video:

• How to download and install Claude Desktop on Mac or Windows.

• A tour of the Cowork interface: tabs, sidebar, workspace, and key controls.

• What the folder boundary is and what "Ask before acting" means before you touch anything.

Welcome back! Last time, we got Cowork installed and took a walk around the interface. Now let’s give it its very first real job.

Covered in the video:

• Watch Cowork plan a filing system and ask for your approval before moving a single file.

• See it sort a messy folder into clean subfolders and flag old files for review.

• How to set up a recurring scheduled task so the cleanup runs itself every month.

Welcome back! Here we are going to learn about two layers of instructions Cowork reads from.

Covered in the video:

• How your existing profile preferences carry into every Cowork session automatically.

• What Global Cowork Instructions are — and why Cowork needs them since it starts fresh each time.

• How to divide your setup between global instructions and Skills.

Welcome back. Let’s set up Cowork global instructions.

Covered in the video:

• A walkthrough of each instruction block: file safety, content types, output format, and session start.

Welcome back.

Now let’s run a new Cowork task and see how the Cowork Global Instructions will impact the task result. And also, let's explore a new Cowork capability — file editing.

Covered in the video:

• How Cowork reads and edits files directly while keeping formatting intact.

• Seeing the Output Format instruction produce a structured table with no extra prompt needed.

• How giving Cowork the right context lets it catch AI-specific terminology errors on its own.

Hey everybody, welcome to the next lecture on Claude Cowork!

From the demos we saw so far, Cowork has only worked with files on your computer. But it can do far more than that.

Covered in the video:

• The three ways Cowork reaches outside your computer — and which one it always tries first.

• Why speed and reliability determine the order: Connector → Browser → screen control.

• What happens when the first path fails, and why Cowork keeps going instead of stopping.

Welcome to the tutorial. Cowork is built to automate work at scale, which means it can save you hours of repetitive, manual effort. So let's put that to the test.

Covered in the video:

• How to set up the Google Drive and Gamma connectors and run a multi-step automation.

• Watch Cowork summarize documents and build slide decks from a Gamma template.

• What granting Drive access really means — and the safest way to set it up.

Welcome to the second part of the tutorial!

Covered in the video:

• How Cowork delegates tasks to an external AI agent in Gamma.

As we discussed at the end of the previous lecture, Cowork demands more from your usage limits than regular chat does. And that's not a flaw — it's actually the point.

Covered in the video:

• How the two limits work — a rolling five-hour window and a weekly cap — and what resets each one.

• Why Cowork draws from your budget faster than regular chat, and what counts toward it.

• How do you get the most out of Cowork without burning through your budget.

In the last lecture, we talked about usage limits. We covered how the rolling window works, why Cowork uses your budget faster than regular chat, how to optimize your usage and where to check how much you have left.

Now let's talk about something equally important.

Covered in the video:

• What it means to give Cowork folder access — and how to keep your sensitive files out of reach.

• What prompt injection is and how to spot it when Cowork starts behaving unexpectedly.

• The approval prompt habit — why you should always read it before you click, and when "Act without asking" is safe to turn on.

In this tutorial we'll explore yet another use-case for Cowork. This time we'll work with a fictional company called Reva AI — an AI receptionist for small businesses like dental offices, restaurants, home services, fitness studios, and cleaning companies. It answers calls, books appointments, and captures leads when staff can't pick up. I'm on the Customer Success team, and I want to understand what our customers think — and then turn that understanding into action.

Covered in the video:

• How to build an interactive feedback dashboard in Cowork using connected data sources.

• What task queuing is — sending the next instruction before the first task has finished.

• How to run a separate Cowork task in parallel while another one is still running in the background.

Welcome to the second part of the tutorial!

Covered in the video:

• How to apply the theme-factory skill to redesign and polish a finished dashboard.

• How to use the Notion connector to turn your analysis into a structured brief, ready for your team.

Welcome to the third and final part of the tutorial!

Covered in the video:

• How to use the Slack connector to send a handoff message directly from Cowork.

• How to create a brand new skill inside Cowork so the Notion Brief can be recreated whenever you need it — without starting from scratch.

Welcome back!

By now, you've seen a few examples of Cowork in action. But I'd guess some of you are sitting thinking: Anna, those are good examples, but they're not quite my job. My work doesn't look like that.

That's a fair reaction.

And it's exactly why I wanted to end this section here — not with another demo of what Cowork does, but with a way for you to figure out what it should do in yours.

Covered in the video:

• How to use Claude's interview skill to uncover repetitive tasks you've stopped noticing.

• How to ask Claude to scan your past conversations for patterns worth automating.

• A five-question checklist to filter which tasks are worth building in Cowork.

  
  

Welcome to the first lecture of this section!

Covered in the video:

• What live artifacts are and how they're different from regular artifacts.

• When to use a live artifact vs. a regular one.

• Safety and limitations to keep in mind.

• Preview of what we'll build in the next tutorial.

Welcome back! Think about what your morning looks like before you start your day.

You check your calendar to see what meetings you have. You open your inbox to see what came in overnight. You check Notion or whatever project tool you use to see where things stand.

Maybe you check Slack too. That's already four different apps pulling your attention in four different directions before you've done any actual work.

What if all of that was in one place, updated every morning without you having to do anything? That's what we're going to build right now.

Covered in the video:

• Creating your first live artifact, Daily Command Center, through Cowork's guided flow.

• Reviewing what Claude builds by default.

• Customizing the visual design of your dashboard.

Welcome to the second part of the tutorial where we build your first live artifact - Daily Command Center.

Covered in the video:

• Filtering each section to show only what matters to you.

• Adding interactivity so you can read details without leaving the dashboard.

• Confirming the artifact updates automatically with fresh data.

Welcome back! So far in this section, you've been running tasks in Cowork — some on demand, some on a schedule. Each one works well on its own.

But what if you're running a content program for your personal brand. Or maybe you're managing a product launch that spans several weeks. Or perhaps you're doing ongoing client reporting where the structure stays the same but the data changes every month.

These aren't one-off tasks. They're initiatives that need Claude to understand the full picture, remember what happened last time, and keep building on it. That's what a Cowork Project gives you.

Covered in the video:

• What Cowork Projects are.

• The three capabilities Cowork Projects add that Chat Projects can't do.

• How memory works across tasks instead of conversations.

Welcome back.

In the next lecture, we're building a Cowork Project for social media content. Before we get there, there's one piece that has to be in place first: your tone of voice.

Covered in the video:

• Why Claude needs a tone of voice skill before it can write content that sounds like you.

• Walking through the full process of creating one, step by step.

• Testing and refining the skill with a real post.

Hey everybody and welcome back to the lecture! In the last lecture, we looked at prototypes in general — why they matter and how they help validate your ideas. Now let’s talk about Claude specifically.

Covered in the video:

• Tools available in Claude for prototyping.

• Follow-along project overview.

In the last lecture, we talked about why business cards still matter and why they’re a great example project to learn prototyping with Claude.

Now, before we jump straight into building, we need a simple plan.

Covered in the video:

• What is a PRD and why do you need it?

• Example: Creating a PRD with Claude.

Now that we have our PRD written with Claude, it’s time for the fun part — actually building our first working version of the business card app.

Covered in the video:

• Building the first app version

In the last tutorial, we built the first version of our business card app — a simple card with placeholders for text and a logo.

Now comes the fun part: customizing it with your own brand assets.

So far, we’ve built a working business card app and customized it with your own logo, colors, and fonts. That’s already powerful.

But what if we could make this app interactive — letting you move things around, resize them, rotate them, and even control which elements sit on top?

That’s exactly what we’re going to do in this tutorial.

This is the second part of the tutorial, where we focus on the app’s interactivity — including image resizing, rotating, and layering.

In this tutorial, we’re going to experiment with adding another feature to our prototype: a style presets dashboard - a simple panel where users can quickly apply predefined styles to their business card designs.

Covered in the video:

• Three-step process to build a prototype.

• Tutorial on adding a style presets dashboard to the prototype (part 1).

This is a second part of the tutorial for building a style presets dashboard for our app.

Covered in the video:

• Tutorial on adding a style presets dashboard to the prototype (part 2).

• Anna’s takeaways on prototyping with Claude Artifacts.

Hey everyone, and welcome to the new lecture!

Let’s explore another powerful prompting technique for working with AI assistants like Claude – the "Think Step-by-Step" approach, also called chain-of-thought prompting.

Covered in the video:

• What chain-of-thought prompting is.

• Two options for implementing chain-of-thought in your conversation with Claude.

Hey everyone, welcome to our second lecture on chain-of-thought prompting. As promised, let’s talk about more advanced techniques for chain-of-thought prompting.

Covered in the video:

• Combining chain-of-thought with role-playing.

• Few-shot chain-of-thought prompting.

• One-shot chain-of-thought prompting.

• Common pitfalls of using chain-of-thought prompting and how to avoid them.

Imagine asking an AI assistant about a recent news event, and it confidently cites a detailed article... that doesn't actually exist. Or asking it about public figures and getting responses that mix real facts with completely made-up details.

These aren't bugs or glitches—they're what we call 'hallucinations' in AI, and they're one of the biggest challenges when working with language models like Claude.

Covered in the video:

• Why AI hallucinations happen.

• How to spot AI hallucinations.

• Practical techniques to get more accurate, reliable responses from Claude.

Hey everyone, welcome to our new tutorial. Here, we are going to work on summarizing long-form content with Claude.

Before we start actual work, let’s spend some time learning what kind of data analysis tasks Claude performs best and when you’d be better off relying on traditional data analysis software.

Covered in the video:

• What is data analysis with Claude.

• Scenarios where Claude performs best for data analysis.

Hey everybody, and welcome to the first tutorial for the data analysis with Claude.

Here we are going to create a project where we’ll handle all the conversations around data analysis for our data set.

Covered in the video:

• Claude Project creation and data upload.

Hello, and welcome to the second tutorial of the data analysis series.

Before starting any analysis, we must understand what data we have, how it connects, and identify any quality issues that could skew results.

Covered in the video:

• Walkthrough: Identifying issues in your data.

Hey everyone, and welcome to the next tutorial on data analysis with Claude.ai - this is the final preparation step before we dive into the actual data analysis and vizualisation - so please stay with me.

Covered in the video:

• Fixing the errors with data identified by Claude on the previous step.

Hey everyone, and welcome to the new tutorial where we’ll begin extracting insights from out data.

Covered in the video:

• Understanding the basic performance metrics from the data we have.

Welcome to the second part of the tutorial where we work on understanding the basic performance metrics from the data we have.

You are presenting to a board of directors next week about next year strategic sales planning and you use Claude to prepare for that meeting.

Covered in the video:

• Building executive dashboards that drive strategic decision.

Welcome to the second part of the tutorial where we are building executive dashboards that drive strategic decision for the upcoming board of directors meeting.

In this tutorial, Anna will show you useful techniques for verifying Claude's analysis and building confidence over time, and a step-by-step validation workflow you can use for any Claude recommendation.

We'll use real examples from our B2B sales data to demonstrate these validation techniques in action.

Covered in the video:

• Systematic validation techniques for checking Claude's work.

• Confidence-building strategies for developing trust over time.

This is the second part of the tutorial where we are learning useful techniques for verifying Claude's analysis and building confidence over time.

Welcome to the new section of the course!
In this lecture, you'll learn how AI is evolving from tools that respond to your instructions into agents that act independently on your behalf.

In the previous video, we talked about where generative AI is heading.

Now let’s talk about how that future actually begins.

In this lecture, we’ll quickly go through how to activate Browser Use and look at a few examples of the kinds of tasks it can help you with.

Covered in the video:

• How to activate Browser Use in under 2 minutes.

• How to create structured documents without touching your keyboard.

• How to let Claude review and resolve document comments automatically.

In this demo, I want to show you a very practical use case for Browser Use — something you could realistically use every single day.

Covered in the video:

• How to automate daily meeting prep.

• Multi-source analysis: calendar + email + documents + web research.

• Preview: Saving this workflow as an automatic daily shortcut.

As you already saw, Browser Use is powerful because it doesn’t just answer questions — it takes action on your behalf.

And anytime you give software the ability to act, there are real risks you need to understand.

Let’s talk about these risks.

Covered in the video:

• The three main risks of agentic AI.

• Five practical safety practices for responsible automation.

• Which tasks to avoid and which are safe to automate.

You don’t want to type long, detailed prompts every single time.
And you definitely don’t want to remember to manually run the same workflow every day or every week.

That’s exactly what shortcuts are for.

Covered in the video:

• How to create shortcuts from conversations or individual prompts.

• Scheduling shortcuts to run automatically at specific times.

• Running shortcuts on-demand with the / command.

• What you need for scheduled automation to work.

Now, as promised, let's talk about site access permissions.

Covered in the video:

• How Anthropic's site permissions protect you (blocklists and action confirmations).

• Building and managing your approved sites list.

Welcome back! Over the next two videos, you'll learn how to teach Claude your workflows step-by-step using Voice Instructions.

Covered in the video:

• When to automate vs. when not to—identifying which tasks benefit from automation vs. those faster done manually.

• Using voice instructions to teach Claude your workflows step-by-step.

Welcome to part two! Here we'll test the workflow we taught Claude and set it to run automatically.

Covered in the video:

• Testing and scheduling your taught workflow to run automatically.