The gap between a generic coding assistant and an AI agent that truly understands YOUR company is enormous. Here's the complete blueprint for building custom AI agents: system context, tools, knowledge retrieval, security, and cost optimization. youtu.be/98yYcWwD95I

We're live! Ask anything about anything. youtube.com/live/EA93bbI...

Fixed replicas are always wrong. You're either wasting resources or under-provisioned. Here's how to build Kubernetes autoscaling that goes from 0→5 replicas based on actual traffic, using tools you probably already have. youtu.be/K0aaB2L3sXI

Built AI inference platform using Kubernetes + Crossplane. One custom resource = any team can deploy a model. No GPU expertise required. Your data never leaves your network. Full walkthrough: youtu.be/odZ4WclCX5s

Goodbye ghostty.org. You'll keep running on my machines forever, but I will never see you again.

We're live... Ask us anything. youtube.com/live/lX4VM6O...

"Just tell the AI how we do things" doesn't scale. Tribal knowledge fails. Copy-pasting docs fails. In this video, I show how a vector database + embeddings + MCP server gives your coding agent real company context—automatically. No more fixing AI output by hand. youtu.be/P-Sv6tKPeLQ

Going live... youtube.com/live/dd9pAta...

Today's AMA session is likely to be violent. There might be yelling, a broken nose or two, blood being spilled, ... We'll have two guests, bitter rivals, each one thinking that the other one is terribly wrong. Wars have been started for less. youtube.com/live/dd9pAta...

Traditional UIs assume predictable data. AI outputs are never predictable. So who designs the UI when you don't know what the data looks like until it appears? I explored two approaches — and why the future of UIs might not be designed by humans at all. 🎥👇 youtu.be/czffWAXTy2Y

Going live... youtube.com/live/JLCIcQp...

"Just use a Mac Studio!" Sure—it'll run a trillion-parameter model about 100x slower than H100s. A Mac Mini can't even fit it in memory. Stop romanticizing self-hosting and look at the actual numbers. New video is live. 🍎💀 https://youtu.be/pWtDTkfNaUU

Going live... youtube.com/live/T7EnrW3...

Commands, MCP tools, Skills, Subagents, Hooks, Plugins, Memories... 🤯 Every week there's a new way to extend coding agents. Let's cut through the noise and explain what each actually does, how they work under the hood, and which ones you should actually use. https://youtu.be/xAIN7YHXfCY

Me: "Find all databases in the cluster" kubectl: *struggles through 356 API definitions* Vector DB + AI: "Found PostgreSQL StatefulSet, CloudNativePG cluster, Qdrant, and an AWS RDS instance" This is how K8s querying should work. New video shows how 👇 https://youtu.be/uUdbQkq5c4k

Going live... youtube.com/live/FhrRq9F...

I got addicted to AI. Now I use it to dub my YouTube videos into other languages automatically. Built a CLI that handles everything - upload, dubbing, translation, scheduling. Here's how I integrated ElevenLabs API into my workflow 🎬 https://youtu.be/_tvKc9kKrhA

AI agents are unpredictable by design. The LLM decides the path, chooses tools, loops as needed. You can't debug what you can't see. Good news: OpenTelemetry tracing works for AI agents too. New video explains how. https://youtu.be/Dh7jAYHcAlo

Going live... youtube.com/live/FF5N7ad...

Going live... youtube.com/live/8BOP3lW...

I wrote a simple prompt. Port's MCP provided the context. Claude Code did the rest. Result? A fully configured developer portal with K8s integration, GitHub sync, and self-service actions. AI + the right context = 🔥 https://youtu.be/6r6ITHCYZ3c

We're live... Ask us anything! youtube.com/live/0-Ls3UG...

Most Dockerfiles in production are security nightmares: running as root, using :latest tags, copying secrets. Writing a good Dockerfile isn't hard, you just need to know the rules. Here's every best practice you need for production-ready containers 🐳 https://youtu.be/ueTe-VQaD7c

AMA is live. Ask anything! youtube.com/live/ezW6DX8...

Ask me anything stars in 30 min. youtube.com/live/ezW6DX8...

Your API is a product. Who's using it? Are they abusing it? Should they even have access? New video on API Management: developer portals, analytics, versioning, monetization with Zuplo review 😤 https://youtu.be/mOy2mhKE2_8

Ask Us Anything session starts in less than an hour. youtube.com/live/glRuo5A...

2025: AI agents went from experiment to reality. 2026: Time to take them seriously. Here are the tools that survived real-world use—from Claude Code to the BACK Stack. 🔧🤖 https://youtu.be/65o_j4E7_lk

"What's the status of my app?" should be a simple question. In Kubernetes, it means checking Deployments, Ingresses, databases, PVCs separately. 😤 I fixed this with a Solution CRD that shows unified status for logical resource groups. https://youtu.be/UEkhIMx6B6E

My team had everything: more money, more experience, control over the rules. But when AI entered the game, most refused to play. They sat on the bench yelling at those who tried. Sound familiar? ⚽🤖 Watch the full story: https://youtu.be/ZEB2pKs2R-Q

Your logs show everything succeeded. Your metrics are green. But requests are still slow. The problem? Each service only sees its own work. Distributed tracing connects the dots. 👇 https://youtu.be/Oa-zqv-EBpw

Going live... youtube.com/live/5VXRQFw...

Stop wasting hours chasing down information that should've been provided upfront. Learn how to transform a chaotic repository into a well-organized project with clear processes & automated workflows. https://youtu.be/gYl3moYa4iI

Going live... Desktop: youtube.com/live/L4RZXAK... Mobile: youtube.com/live/mKvsQW6...

See you all later today in this week's AMA session. YouTube (desktop): youtube.com/live/L4RZXAK... YouTube (mobile): youtube.com/live/mKvsQW6...

I wanted to love kagent for Kubernetes, but the UX is painful compared to Claude Code or Cursor 😬 Declarative agents = system prompts + tools + LLM. Nothing you couldn't build yourself in an hour. Full breakdown of what works (and what doesn't) 👇 https://youtu.be/3jkGJvmUMYE

We're live! youtube.com/live/0TtOJbM...

AMA sessions starts in 30 min.... youtube.com/live/0TtOJbM...

Stop trusting day-one AI reviews. I used Gemini 3 exclusively for a week on production code. Yes it's fast. Yes it's smart. But it ignores context, resists feedback, and declares victory while builds fail. https://youtu.be/AUoqr5r1pBY

Going live... youtube.com/live/tafANChjv3g?si=GfwH0woCqgM82KU8

This week's AMA is starting soon. Prepare your questions. www.youtube.com/live/tafANCh...

Stop debugging Kubernetes at 3 AM. I built an AI agent + K8s controller that: ✅ Detects issues via events ✅ Analyzes root cause (99% confidence) ✅ Suggests fixes ✅ Validates remediation Fully open source. https://youtu.be/UbPyEelCh-I

Here's what most devs get wrong about AI agents: The agent is the ONLY dumb actor in the system. It doesn't think or decide—it just executes. The LLM provides the brains, you provide intent. https://youtu.be/bfBOn2Ahj4c

Which AI model for DevOps work? I ran GPT-5, Claude, Gemini, Grok & more through real agent workflows. Pattern recognition, policy generation, troubleshooting. The winner beat models 20x more expensive. https://youtu.be/r84kQ5IMIQM

Going live... youtube.com/live/-nYVMVQ...

AMA starts in 20 minutes. youtube.com/live/-nYVMVQ...

Stop using AI for everything in Kubernetes. Use it where it actually helps: ❌ Alerting (events are better) ✅ Analysis (AI excels here) ⚖️ Remediation (only for unknowns) Smart automation beats expensive AI every time. https://youtu.be/rIdcJYLtCdo

Going live... youtube.com/live/--z0NqQ...

It's Thursday, and that means Ask Us Anything live session. youtube.com/live/--z0NqQ...

MCP servers are just servers. Deploy them like production services: Kubernetes for flexibility, cloud platforms for convenience, but never locally for teams. Full comparison of all methods 👇 https://youtu.be/MHf-M8qOogY