add videos

kentcdodds · kentcdodds · commit 2c791bd73f95 · 2025-09-24T09:31:57.000-06:00
diff --git a/exercises/01.advanced-tools/01.problem.annotations/README.mdx b/exercises/01.advanced-tools/01.problem.annotations/README.mdx
@@ -1,5 +1,7 @@
 # Annotations
 
+<EpicVideo url="https://www.epicai.pro/workshops/day-3-advanced-tools-sampling-and-elicitation/annotations~n6qo2" />
+
 👨‍💼 Users want to feel confident about what each tool in the system does before they use it. They want to know if a tool is safe, if it will change their data, or if it might reach out to the outside world. When tools are clearly labeled for their behavior, the app feels more transparent and trustworthy.
 
 For example, if a tool is read-only, the UI can show a reassuring message. If a tool might delete data, the user should get a warning. If a tool is safe to run multiple times, that's useful to know too. These labels help users make informed decisions and reduce anxiety about using advanced features.
diff --git a/exercises/01.advanced-tools/01.solution.annotations/README.mdx b/exercises/01.advanced-tools/01.solution.annotations/README.mdx
@@ -1,5 +1,7 @@
 # Annotations
 
+<EpicVideo url="https://www.epicai.pro/workshops/day-3-advanced-tools-sampling-and-elicitation/annotations~n6qo2/solution" />
+
 👨‍💼 Fantastic progress! We've successfully introduced annotations to our journaling tools. Now, each tool clearly communicates its intent—whether it's read-only, destructive, idempotent, or open world. This means users and the system can better understand the impact of each action, leading to a safer and more predictable journaling experience. For example, deleting an entry is now marked as idempotent, while creating a tag is clearly non-destructive. These improvements help ensure that users can confidently manage their journal and tags, knowing exactly what each tool is designed to do.
 
 Let's keep up the momentum as we continue to enhance the user experience!
diff --git a/exercises/01.advanced-tools/02.problem.structured/README.mdx b/exercises/01.advanced-tools/02.problem.structured/README.mdx
@@ -1,5 +1,7 @@
 # Structured Output
 
+<EpicVideo url="https://www.epicai.pro/workshops/day-3-advanced-tools-sampling-and-elicitation/structured-output~egacc" />
+
 👨‍💼 When users open EpicMe, they expect their memories, reflections, and daily adventures to be organized, discoverable, and (most importantly) reliable. Imagine a user writing a heartfelt entry about their day, only to have it saved as a jumbled scroll of text! That would be chaos in their personal archive.
 
 To ensure every tool in EpicMe returns information that is both predictable and easy for the UI (and our friendly LLM assistants) to understand, we use **structured output**. This means every tool response follows a clear, machine-validated shape—no more wild guesses or mysterious blobs of data.
diff --git a/exercises/01.advanced-tools/02.solution.structured/README.mdx b/exercises/01.advanced-tools/02.solution.structured/README.mdx
@@ -1,5 +1,7 @@
 # Structured Output
 
+<EpicVideo url="https://www.epicai.pro/workshops/day-3-advanced-tools-sampling-and-elicitation/structured-output~egacc/solution" />
+
 👨‍💼 Outstanding achievement! We've now brought structured output to our journaling tools, ensuring every action in EpicMe returns information in a clear, machine-validated format. This means users can trust that their memories, reflections, and daily adventures are always organized and reliably presented—no more cryptic or unpredictable responses. The UI can now display journal entries, tags, and magical creatures (😉) with confidence, knowing exactly what to expect from each tool. This upgrade not only makes the experience more seamless and delightful for our users, but also paves the way for smarter automation and safer interactions throughout the app.
 
 With structured output in place, EpicMe is even better equipped to help users capture and revisit their stories, making every journaling moment feel effortless and secure. Let's keep building on this momentum!
diff --git a/exercises/01.advanced-tools/FINISHED.mdx b/exercises/01.advanced-tools/FINISHED.mdx
@@ -1,3 +1,5 @@
 # Advanced Tools
 
+<EpicVideo url="https://www.epicai.pro/workshops/day-3-advanced-tools-sampling-and-elicitation/break~70afq" />
+
 Awesome work. You now understand about annotations, structured output, and output schemas. Hopefully this enables you to take advantage of great client features when clients support these features.
diff --git a/exercises/01.advanced-tools/README.mdx b/exercises/01.advanced-tools/README.mdx
@@ -1,5 +1,7 @@
 # Advanced Tools
 
+<EpicVideo url="https://www.epicai.pro/workshops/day-3-advanced-tools-sampling-and-elicitation/intro~2nnka" />
+
 ## Tool Annotations
 
 Tool annotations are metadata attached to each tool definition. They help clients and users understand the tool's behavior, especially regarding side effects, safety, and intended use. Annotations do **not** affect the tool's execution. They are hints for UI, approval flows, and documentation.
diff --git a/exercises/02.elicitation/01.problem/README.mdx b/exercises/02.elicitation/01.problem/README.mdx
@@ -1,5 +1,7 @@
 # Elicit Confirmation
 
+<EpicVideo url="https://www.epicai.pro/workshops/day-3-advanced-tools-sampling-and-elicitation/elicit-confirmation~oaha2" />
+
 👨‍💼 When users interact with our system, they sometimes initiate actions that have significant consequences (like deleting a tag or entry). To ensure users don't accidentally lose something important, we need to pause and ask for explicit confirmation before proceeding.
 
 This is where **elicitation** comes in. Instead of making assumptions, our MCP server can make a structured elicitation request. This lets us ask the user for confirmation in a way that's both clear and robust, and ensures the server only proceeds if the user truly intends to take the action.
diff --git a/exercises/02.elicitation/01.solution/README.mdx b/exercises/02.elicitation/01.solution/README.mdx
@@ -1,5 +1,7 @@
 # Elicit Confirmation
 
+<EpicVideo url="https://www.epicai.pro/workshops/day-3-advanced-tools-sampling-and-elicitation/elicit-confirmation~oaha2/solution" />
+
 👨‍💼 Fantastic progress! We've just introduced a robust confirmation step for destructive actions, such as deleting a tag. Now, whenever a user initiates an action that could have significant consequences, the system pauses and asks for explicit confirmation using a structured elicitation prompt. This ensures that users are always in control and never accidentally lose important data.
 
 By leveraging the Model Context Protocol's elicitation feature, our app now provides a clear, user-friendly dialog that requests confirmation before proceeding. If the user decides not to confirm, the action is gracefully cancelled and the user receives immediate feedback—no tags are deleted unless the user truly intends it.
diff --git a/exercises/02.elicitation/FINISHED.mdx b/exercises/02.elicitation/FINISHED.mdx
@@ -1,3 +1,5 @@
 # Elicitation
 
+<EpicVideo url="https://www.epicai.pro/workshops/day-3-advanced-tools-sampling-and-elicitation/break~pa6st" />
+
 Awesome job! You now know how to elicit input from the user while your tools are running, making your MCP server user experience that much better.
diff --git a/exercises/02.elicitation/README.mdx b/exercises/02.elicitation/README.mdx
@@ -1,5 +1,7 @@
 # Elicitation
 
+<EpicVideo url="https://www.epicai.pro/workshops/day-3-advanced-tools-sampling-and-elicitation/intro~gs3h2" />
+
 Modern AI applications often need to collect structured input from users at key moments in a workflow. **Elicitation** in the Model Context Protocol (MCP) standardizes this process, allowing servers to request information from users through the client, using a well-defined schema and a secure, user-friendly interaction model.
 
 Elicitation enables interactive workflows like confirming destructive actions, collecting additional details, or guiding users through multi-step forms by letting the server pause and ask the user for exactly what it needs, in a structured way.
diff --git a/exercises/03.sampling/01.problem.simple/README.mdx b/exercises/03.sampling/01.problem.simple/README.mdx
@@ -1,5 +1,7 @@
 # Simple Sampling
 
+<EpicVideo url="https://www.epicai.pro/workshops/day-3-advanced-tools-sampling-and-elicitation/simple-sampling~5yj44" />
+
 👨‍💼 Our users love the prompt functionality, but they asked why the LLM couldn't
 just suggest tags when they create the post and we thought that's a great idea!
 
diff --git a/exercises/03.sampling/01.solution.simple/README.mdx b/exercises/03.sampling/01.solution.simple/README.mdx
@@ -1,5 +1,7 @@
 # Simple Sampling
 
+<EpicVideo url="https://www.epicai.pro/workshops/day-3-advanced-tools-sampling-and-elicitation/simple-sampling~5yj44/solution" />
+
 👨‍💼 Great! Now we're wired up to ask the LLM to do stuff for us. Let's get to
 that next.
 
diff --git a/exercises/03.sampling/02.problem.advanced/README.mdx b/exercises/03.sampling/02.problem.advanced/README.mdx
@@ -1,5 +1,7 @@
 # Advanced Sampling Prompt
 
+<EpicVideo url="https://www.epicai.pro/workshops/day-3-advanced-tools-sampling-and-elicitation/advanced-sampling-prompt~qyf7c" />
+
 👨‍💼 Now that you've wired up basic sampling, it's time to make your prompt
 have the LLM do something actually useful! Instead of just asking for a generic
 response, you'll craft a prompt that enables the model to suggest relevant tags
diff --git a/exercises/03.sampling/02.solution.advanced/README.mdx b/exercises/03.sampling/02.solution.advanced/README.mdx
@@ -1,5 +1,7 @@
 # Advanced Sampling Prompt
 
+<EpicVideo url="https://www.epicai.pro/workshops/day-3-advanced-tools-sampling-and-elicitation/advanced-sampling-prompt~qyf7c/solution" />
+
 👨‍💼 Hooray! Now our users can get tag suggestions from the LLM when they create a
 new journal entry and have those actually be created and applied! Cool!
 
diff --git a/exercises/03.sampling/FINISHED.mdx b/exercises/03.sampling/FINISHED.mdx
@@ -1,4 +1,6 @@
 # Sampling
 
+<EpicVideo url="https://www.epicai.pro/workshops/day-3-advanced-tools-sampling-and-elicitation/break~iezdw" />
+
 Great! Our users are happy with the sampling functionality you've
 implemented. It's really turning their assistant into an actual assistant!
diff --git a/exercises/03.sampling/README.mdx b/exercises/03.sampling/README.mdx
@@ -1,5 +1,7 @@
 # Sampling
 
+<EpicVideo url="https://www.epicai.pro/workshops/day-3-advanced-tools-sampling-and-elicitation/intro~0dyu8" />
+
 Modern AI applications often need to generate new content (whether that's text,
 images, or more) on demand. This process is called **sampling**: asking a
 language model (or other generative model) to produce a completion or response
@@ -13,12 +15,7 @@ This one is a tricky one to understand. Think of it like you're "borrowing" the
 user's LLM to generate content for them.
 [Read about this idea here](https://www.epicai.pro/how-to-use-sampling-in-mcp-borrow-the-users-llm-o7nk3).
 
-It may be helpful for you to watch a demo of this working:
-
-<EpicVideo
-	title="Using MCP Sampling in VSCode"
-	url="https://www.epicai.pro/using-mcp-sampling-in-vs-code-insiders-dd12d"
-/>
+You can watch another [demo of this working here](https://www.epicai.pro/using-mcp-sampling-in-vs-code-insiders-dd12d).
 
 <callout-success>
 	From [the MCP
diff --git a/exercises/04.long-running-tasks/01.problem.progress/README.mdx b/exercises/04.long-running-tasks/01.problem.progress/README.mdx
@@ -1,5 +1,7 @@
 # Progress Updates
 
+<EpicVideo url="https://www.epicai.pro/workshops/day-3-advanced-tools-sampling-and-elicitation/progress-updates~a3g0l" />
+
 👨‍💼 When users ask our mcp server to generate their journal wrapped video, it can take some time and they want to know that things are moving along. Nobody likes staring at a blank screen, wondering if the app is frozen or if their request was even received. Progress updates are how we keep users in the loop, making the wait feel shorter and the experience more delightful.
 
 Here's an example of how to perform progress updates in your MCP server:
diff --git a/exercises/04.long-running-tasks/01.solution.progress/README.mdx b/exercises/04.long-running-tasks/01.solution.progress/README.mdx
@@ -1,5 +1,7 @@
 # Progress Updates
 
+<EpicVideo url="https://www.epicai.pro/workshops/day-3-advanced-tools-sampling-and-elicitation/progress-updates~a3g0l/solution" />
+
 👨‍💼 Fantastic news! We've just made waiting for a journal wrapped video a much better experience. Now, when users request their video, they receive real-time progress updates throughout the process. Instead of staring at a blank screen and wondering if anything is happening, users see clear, friendly notifications that keep them in the loop from start to finish.
 
 This means users always know their request is being handled, and they can follow along as their video is assembled—making the wait feel shorter and the experience more delightful. Progress updates transform a long-running task into a transparent, engaging journey, building trust and satisfaction with every step.
diff --git a/exercises/04.long-running-tasks/02.problem.cancellation/README.mdx b/exercises/04.long-running-tasks/02.problem.cancellation/README.mdx
@@ -1,5 +1,7 @@
 # Cancellation
 
+<EpicVideo url="https://www.epicai.pro/workshops/day-3-advanced-tools-sampling-and-elicitation/cancellation~6o5mm" />
+
 👨‍💼 When users embark on creating their personalized wrapped video, the process can take a while (especially if they journal a lot). Sometimes, halfway through, they realize they picked the wrong year, or maybe their cat walks across the keyboard and they want to stop the operation immediately. It's essential that our app gives users the power to cancel these long-running tasks, so they always feel in control and never stuck waiting for something they no longer want.
 
 Let's make sure users can hit the "Stop" button and have their request canceled right away, freeing up system resources and making the experience feel responsive and modern.
diff --git a/exercises/04.long-running-tasks/02.solution.cancellation/README.mdx b/exercises/04.long-running-tasks/02.solution.cancellation/README.mdx
@@ -1,5 +1,7 @@
 # Cancellation
 
+<EpicVideo url="https://www.epicai.pro/workshops/day-3-advanced-tools-sampling-and-elicitation/cancellation~6o5mm/solution" />
+
 👨‍💼 Outstanding progress! We've just empowered our users with the ability to cancel long-running operations—like generating their personalized wrapped video—at any time. This means that if a user changes their mind, makes a mistake, or simply needs to stop the process, they can do so instantly, without waiting for the task to finish.
 
 This enhancement puts users in control, making the app feel faster, more flexible, and responsive. No more feeling stuck or frustrated by accidental requests or long waits. And it's more efficient for our servers as well to not continue processing a request that was cancelled. Now, users can confidently start and stop operations as needed, knowing the system will respect their choices and free up resources right away.
diff --git a/exercises/04.long-running-tasks/FINISHED.mdx b/exercises/04.long-running-tasks/FINISHED.mdx
@@ -1,3 +1,5 @@
 # Long Running Tasks
 
+<EpicVideo url="https://www.epicai.pro/workshops/day-3-advanced-tools-sampling-and-elicitation/break~j3a9t" />
+
 You can now manage long-running tasks in your tools, reporting progress and allowing users to cancel operations. Good job!
diff --git a/exercises/04.long-running-tasks/README.mdx b/exercises/04.long-running-tasks/README.mdx
@@ -1,5 +1,7 @@
 # Long Running Tasks
 
+<EpicVideo url="https://www.epicai.pro/workshops/day-3-advanced-tools-sampling-and-elicitation/intro~wjyc8" />
+
 In this exercise, you'll learn how to handle long-running tasks in the context of the Model Context Protocol (MCP), with a focus on **progress reporting** and **cancellation**. (As a bonus, you'll also get hands-on experience with JavaScript's `AbortController` and signals, which are essential for managing asynchronous operations that can be cancelled).
 
 ## Background
diff --git a/exercises/05.changes/01.problem.list-changed/README.mdx b/exercises/05.changes/01.problem.list-changed/README.mdx
@@ -1,5 +1,7 @@
 # List Changed
 
+<EpicVideo url="https://www.epicai.pro/workshops/day-3-advanced-tools-sampling-and-elicitation/list-changed~43sfe" />
+
 👨‍💼 When people use the Epic Me journal app, they expect the interface to always reflect what's possible right now. If a new journaling prompt becomes available, or a feature is temporarily disabled, users want the UI to update instantly. No confusion, no stale buttons, just a smooth, up-to-date experience.
 
 That's why it's so important for our MCP server to notify the client whenever the set of available prompts, tools, or resources changes. This allows the client app to feel alive and responsive, and ensures users always see the right options for their current context, whether they're a first-time journaler or a seasoned reflection pro.
diff --git a/exercises/05.changes/01.solution.list-changed/README.mdx b/exercises/05.changes/01.solution.list-changed/README.mdx
@@ -1,5 +1,7 @@
 # List Changed
 
+<EpicVideo url="https://www.epicai.pro/workshops/day-3-advanced-tools-sampling-and-elicitation/list-changed~43sfe/solution" />
+
 👨‍💼 Fantastic progress! Our app now supports real-time updates for journaling
 prompts, thanks to the new `list_changed` notification capability. Whenever a
 prompt is enabled or disabled (like when a new journaling feature becomes
diff --git a/exercises/05.changes/02.problem.resources-list-changed/README.mdx b/exercises/05.changes/02.problem.resources-list-changed/README.mdx
@@ -1,5 +1,7 @@
 # Resource Template List Changed
 
+<EpicVideo url="https://www.epicai.pro/workshops/day-3-advanced-tools-sampling-and-elicitation/resource-template-list-changed~lkds0" />
+
 👨‍💼 When people use our EpicMe journaling app, they expect the list of available resources (like journal entries, tags, or even videos) to always reflect what's actually possible right now. Imagine a user just added a new video reflection or created a fresh tag for their latest entry. They want to see those options appear instantly, without needing to refresh or wonder if something is out of sync.
 
 That's why it's so important for our MCP server to notify the client whenever the set of available resources changes, especially when those resources are managed by templates that can expand or contract as the underlying data changes. This keeps the UI feeling alive and responsive, so users always see the right options for their current context, whether they're a first-time journaler or a seasoned reflection pro.
diff --git a/exercises/05.changes/02.solution.resources-list-changed/README.mdx b/exercises/05.changes/02.solution.resources-list-changed/README.mdx
@@ -1,5 +1,7 @@
 # Resource Template List Changed
 
+<EpicVideo url="https://www.epicai.pro/workshops/day-3-advanced-tools-sampling-and-elicitation/resource-template-list-changed~lkds0/solution" />
+
 👨‍💼 Outstanding work! Our app now keeps the list of available resources—like journal entries, tags, and videos—perfectly in sync with what's actually possible for the user, thanks to the new `list_changed` notification for resource templates. Now, whenever a user adds a new video reflection, creates a fresh tag, or updates their journal, the UI updates instantly.
 
 Let's keep going!
diff --git a/exercises/05.changes/03.problem.subscriptions/README.mdx b/exercises/05.changes/03.problem.subscriptions/README.mdx
@@ -1,5 +1,7 @@
 # Subscriptions
 
+<EpicVideo url="https://www.epicai.pro/workshops/day-3-advanced-tools-sampling-and-elicitation/subscriptions~hja2q" />
+
 👨‍💼 When people use our EpicMe journaling MCP, they want the LLM they're using to always have the latest version of their jounraling data. Exposing subscriptions for resources (like a particular entry, tag, or video) allows clients to be notified of changes to specific resources the LLM is using in its context or the client may be using for other purposes.
 
 To make this possible, our MCP server needs to support **resource subscriptions**. This means clients can subscribe to updates for specific resources, and the server will notify them when those resources change.
diff --git a/exercises/05.changes/03.solution.subscriptions/README.mdx b/exercises/05.changes/03.solution.subscriptions/README.mdx
@@ -1,5 +1,7 @@
 # Subscriptions
 
+<EpicVideo url="https://www.epicai.pro/workshops/day-3-advanced-tools-sampling-and-elicitation/subscriptions~hja2q/solution" />
+
 👨‍💼 Way to go! We've just unlocked real-time updates for our users by enabling resource subscriptions. Now, whenever someone is working with a specific journal entry, tag, or video, the app can instantly notify them of any changes—no more stale data or manual refreshes. This means users always have the most up-to-date information at their fingertips, making their journaling experience seamless and trustworthy.
 
 By supporting the `subscribe` capability, we've ensured that our app feels alive and responsive, keeping users in sync with their most important content. This is a huge win for anyone who relies on timely, accurate updates—whether they're reflecting on their latest entry, organizing tags, or reviewing a video.
diff --git a/exercises/05.changes/FINISHED.mdx b/exercises/05.changes/FINISHED.mdx
@@ -1,3 +1,5 @@
 # Changes
 
+<EpicVideo url="https://www.epicai.pro/workshops/day-3-advanced-tools-sampling-and-elicitation/break~yv13f" />
+
 Great job on this exercise. You now know how to make dynamic MCP servers.
diff --git a/exercises/05.changes/README.mdx b/exercises/05.changes/README.mdx
@@ -1,5 +1,7 @@
 # Changes
 
+<EpicVideo url="https://www.epicai.pro/workshops/day-3-advanced-tools-sampling-and-elicitation/intro~s3qik" />
+
 In a web application, the buttons, links, and data that you see change based on the context. Whether the user is currently logged in, whether there is any data available, what role the user has, etc. MCP servers are no different. The information and tools they provide can change at any time.
 
 MCP provides a robust system for **notifying clients about changes** so that UIs and agents can stay in sync with the server's current capabilities and data.
diff --git a/exercises/FINISHED.mdx b/exercises/FINISHED.mdx
@@ -1,3 +1,5 @@
 # Advanced MCP Features 🐡
 
+<EpicVideo url="https://www.epicai.pro/workshops/day-3-advanced-tools-sampling-and-elicitation/outro-you-ve-finished-advanced-mcp~ly753" />
+
 Thank you for joining me for this workshop. I hope you have a much better understanding of the more advanced capabilities of MCP servers!
diff --git a/exercises/README.mdx b/exercises/README.mdx
@@ -1,5 +1,7 @@
 # Advanced MCP Features 🐡
 
+<EpicVideo url="https://www.epicai.pro/workshops/day-3-advanced-tools-sampling-and-elicitation/intro-learn-advanced-features-for-better-ux~zuzak" />
+
 👨‍💼 Hello, my name is Peter the Product Manager. I'm here to help you get
 oriented and to give you your assignments for the workshop!
 
diff --git a/package.json b/package.json
@@ -18,6 +18,7 @@
     },
     "product": {
       "host": "www.epicai.pro",
+      "slug": "day-3-advanced-tools-sampling-and-elicitation",
       "displayName": "EpicAI.pro",
       "displayNameShort": "Epic AI"
     }
