docs(prompt): add guide videos to all six prompt guides

src/pages/docs/prompt/guides/commit-and-compare-versions.mdx

@@ -5,6 +5,16 @@ description: "Turn a working draft into a version you can point to, then compare
 
 A prompt starts out as a [draft](/docs/prompt/concepts/versions-and-labels) you're still editing. Running it once and committing turns that draft into a version, one that sticks around after you move on to the next edit.
 
+<video
+  autoPlay
+  muted
+  loop
+  playsInline
+  className="w-full rounded-xl shadow-lg"
+  src="/images/docs/prompt/guides/commit-and-compare-versions.mp4"
+/>
+*History opens from the editor header; Commit History lists every commit*
+
 ## Commit a version
 
 This picks up with the support-agent template already open in the editor, either fresh from [Create a prompt](/docs/prompt/guides/create-a-prompt) or one you're mid-edit on.

src/pages/docs/prompt/guides/create-a-prompt.mdx

@@ -17,6 +17,17 @@ Every prompt starts in the same place: the [Prompts](/docs/prompt/concepts/under
   </Step>
 </Steps>
 
+<video
+  autoPlay
+  muted
+  loop
+  playsInline
+  className="w-full rounded-xl shadow-lg"
+  src="/images/docs/prompt/guides/create-a-prompt.mp4"
+/>
+*Start from scratch, name it, pick a model, write the messages, then run it*
+
+
 ## Pick a starting point
 
 ### Generate with AI

src/pages/docs/prompt/guides/evaluate-prompt-outputs.mdx

@@ -31,6 +31,17 @@ The **Evaluation** tab stays disabled until the template has at least one output
   </Step>
 </Steps>
 
+<video
+  autoPlay
+  muted
+  loop
+  playsInline
+  className="w-full rounded-xl shadow-lg"
+  src="/images/docs/prompt/guides/evaluate-prompt-outputs.mp4"
+/>
+*The Evaluation tab scores each output against the evals attached to the prompt*
+
+
 ## Read the results next to each output
 
 Each attached eval's score lands in its own column, next to the output it scored, so you can scan outputs and scores together instead of cross-referencing two views.

src/pages/docs/prompt/guides/organize-prompts-in-folders.mdx

@@ -33,6 +33,17 @@ This guide assumes you already have a prompt to organize, for example `support-a
   </Step>
 </Steps>
 
+<video
+  autoPlay
+  muted
+  loop
+  playsInline
+  className="w-full rounded-xl shadow-lg"
+  src="/images/docs/prompt/guides/organize-prompts-in-folders.mp4"
+/>
+*New Folder, then Move a prompt into it from its row menu*
+
+
 ## Rename a folder or a prompt
 
 Open the row menu for a folder or a prompt (`support-agent`, for example) and select **Rename**. Update the name and click **Save**. Both folder names and prompt names must be unique within your workspace, so renaming to a name already in use is rejected.

src/pages/docs/prompt/guides/run-a-prompt.mdx

@@ -5,6 +5,16 @@ description: "Write messages, set variables and parameters, and run a prompt in
 
 The **Playground** tab is where an open template turns into a model response. This guide picks up with a template already open, either a fresh one from [Create a prompt](/docs/prompt/guides/create-a-prompt) or the support-agent prompt built here, using the same running example as [Understanding Prompts](/docs/prompt/concepts/understanding-prompts).
 
+<video
+  autoPlay
+  muted
+  loop
+  playsInline
+  className="w-full rounded-xl shadow-lg"
+  src="/images/docs/prompt/guides/run-a-prompt.mp4"
+/>
+*Open a prompt, click Run Prompt, and the response lands in Output*
+
 The Playground splits into two panels. The left panel is the **editor**: your messages, with a header row above them for the model picker and its parameters. The toolbar at the top of the workbench holds the **Variables** control and **Run Prompt**. The right panel is the **output panel**, where the response appears once you run the prompt.
 
 ## Write the messages

src/pages/docs/prompt/guides/track-prompt-performance.mdx

@@ -35,6 +35,17 @@ The **Metrics** tab stays disabled until the prompt has produced at least one ou
   </Step>
 </Steps>
 
+<video
+  autoPlay
+  muted
+  loop
+  playsInline
+  className="w-full rounded-xl shadow-lg"
+  src="/images/docs/prompt/guides/track-prompt-performance.mp4"
+/>
+*Metrics and Linked Traces for the prompt's live traffic*
+
+
 ## Drill into the traces behind a number
 
 Switch to the **Linked Traces** sub-tab to see the individual traces that rolled up into those numbers, useful when a median looks off and you want to check what actually produced it.