docs: Update Sebastian Maniak's author details and add a title to the human-in-the-loop kagent blog post.

Signed-off-by: Sebastian Maniak <sebastian@maniak.io>

Author: sebastianmaniak

src/app/blog/authors.ts

@@ -38,9 +38,9 @@ export const authors: Author[] = [
   {
     id: "sebastianmaniak",
     name: "Sebastian Maniak",
-    title: "Field CTO",
-    photo: "/images/authors/sebastianmaniak.jpg",
-    bio: "Sebastian Maniak is a Field CTO at Solo.io, helping organizations adopt cloud-native technologies and AI-powered infrastructure.",
+    title: "Technical Product Marketing Manager",
+    photo: "/images/authors/sebastianmaniak.png",
+    bio: "Sebastian Maniak is a Technical Product Marketing Manager at Solo.io, focused on AI and helping organizations adopt AI-powered infrastructure.",
   },
   {
     id: "michaellevan",

src/blogContent/human-in-the-loop-kagent.mdx

@@ -7,6 +7,8 @@ export const metadata = {
   authorIds: ["sebastianmaniak"],
 };
 
+# How to build Kubernetes-native AI agents that pause and ask for approval before taking destructive actions, using kagent's human-in-the-loop capabilities.
+
 AI agents are getting good — really good — at taking autonomous action. They can inspect your Kubernetes cluster, diagnose problems, create resources, and even clean up after themselves. But here's the uncomfortable question most teams are quietly asking:
 
 *"Do I actually want an AI agent deleting things in my production cluster without asking me first?"*