Replace Loom video in AI agents getting started guide (#273)

* Update guides/ai-agents/getting-started.mdx

Co-Authored-By: mintlify[bot] <109931778+mintlify[bot]@users.noreply.github.com>

* Update guides/ai-agents/using-ai-agents.mdx

Co-Authored-By: mintlify[bot] <109931778+mintlify[bot]@users.noreply.github.com>

* Update guides/ai-agents/data-access.mdx

Co-Authored-By: mintlify[bot] <109931778+mintlify[bot]@users.noreply.github.com>

* Documentation edits made through Mintlify web editor

---------

Co-authored-by: mintlify[bot] <109931778+mintlify[bot]@users.noreply.github.com>

Author: mintlify[bot]

guides/ai-agents/data-access.mdx

@@ -63,6 +63,20 @@ You can control which explores and fields your AI agent can access using tags. W
 1. **Explore-level tags** - Tag the model to control access to entire explores
 2. **Field-level tags** - Tag individual metrics and dimensions for granular control
 
+Watch this demo to see tag-based access control in action:
+
+<Frame>
+  <iframe
+    width="100%"
+    height="420"
+    src="https://www.loom.com/embed/f38e27fee7784e7f95538613b3b77bb5?sid=a13feb5b-fef3-4f68-9fbf-e54f928c28e5"
+    frameborder="0"
+    webkitallowfullscreen
+    mozallowfullscreen
+    allowfullscreen
+  />
+</Frame>
+
 ### How filtering works
 
 The filtering behavior depends on how you've tagged your models:

guides/ai-agents/getting-started.mdx

@@ -176,7 +176,7 @@ You can create multiple AI agents, each configured for different tasks, tones, l
   <iframe
     width="100%"
     height="420"
-    src="https://www.loom.com/embed/26adbd03cf2049ddb81e015f9756a4bb?sid=dae39714-3c86-4254-af23-bb2def551fba"
+    src="https://www.loom.com/embed/50bcb0d6f26b428bae336139d9d64e22"
     frameborder="0"
     webkitallowfullscreen
     mozallowfullscreen

guides/ai-agents/using-ai-agents.mdx

@@ -20,22 +20,6 @@ As mentioned earlier, Lightdash agents use the **semantic layer** defined in you
 This ensures that the AI generates accurate queries and visualizations based on your specific data context.
 So, *when an Agent generates an answer, the output is a semantic query, **not SQL!*** This means that you can easily swap between the conversational AI interface and the standard Lightdash exploration experience.
 
-## Demo
-
-Watch this comprehensive demo to see AI agents in action:
-
-<Frame>
-  <iframe
-    width="100%"
-    height="420"
-    src="https://www.loom.com/embed/f38e27fee7784e7f95538613b3b77bb5?sid=a13feb5b-fef3-4f68-9fbf-e54f928c28e5"
-    frameborder="0"
-    webkitallowfullscreen
-    mozallowfullscreen
-    allowfullscreen
-  />
-</Frame>
-
 ## FAQs
 
 1. Does Lightdash store the query data?