Advertise on podcast: The Private AI Lab

NVIDIA just shipped a model with four times the context window of what's been running my home agent for months. So I swapped it in, broke my own setup within the first hour, and then threw 700,000 words at it to see if it would lie to me. No guest this episode, just me and my home lab. Jarvis, my home agent, has been running on Qwen3.6-35B-A3B since the start, served through vLLM on the DGX Spark's 128GB of unified memory. Then NVIDIA released Nemotron 3.5 Lightning 30B-A3B in NVFP4, and one number stopped me mid-scroll: a validated 1 million token context window, four times what Qwen gives you at 262,000.I don't trust a spec sheet claim until I've broken it myself, so I swapped the model into Jarvis, found a memory reservation bug in NVIDIA's own deployment recipe within the first hour, fixed it, and then buried a fabricated secret code word 90% of the way through a 700,000 word document to see if the model could actually recall it. I also dug into DSpark, the speculative decoding checkpoint built specifically for this hardware, and measured what it actually does for throughput. This episode is the honest version: what's proven on my own hardware, what's still sitting on NVIDIA's spec sheet, and what I still don't know about whether Nemotron makes Jarvis a better agent day to day. Key topics covered: Why Jarvis's setup (Qwen3.6-35B-A3B on vLLM) needed an indirection layer before any of this matteredNVIDIA Nemotron 3.5 Lightning 30B-A3B-NVFP4's validated 1 million token context window, tested against a 700,000-word documentThe memory reservation bug in NVIDIA's DGX Spark deployment recipe, and the one-line fixDSpark speculative decoding: how it works, and the acceptance rate that made it worth usingNemotron's hybrid Mamba-2, attention, and mixture-of-experts architecture, and why it matters for running 1M tokens on a single boxWhat's proven on real hardware versus what's still just NVIDIA's own benchmark numbersWhy Nemotron isn't confirmed as the better agent brain for Jarvis yet Chapters 00:00 Introduction — what a 1M-token context window actually changes 00:37 Welcome back to The Private AI Lab (no guest this episode) 01:19 Recap: Jarvis running on Qwen3.6-35B-A3B via vLLM on the DGX Spark 01:58 NVIDIA Nemotron 3.5 Lightning lands with a validated 1M-token window 02:49 Deployment: why the Jarvis-LLM alias made the model swap painless 03:28 The memory reservation bug NVIDIA's own recipe doesn't warn about 04:53 The test: a 700,000-word document with one hidden code word 05:51 DSpark speculative decoding: free speed, fully verified 06:47 The reasoning quirk that quietly eats your token budget 07:31 Nemotron vs Qwen: what's proven versus what's still a spec sheet claim 08:01 The hybrid architecture behind why 1M tokens fits on a DGX Spark 09:24 NVIDIA's own SWE-bench Verified numbers, and their limits 09:56 Closing thoughts, and what's coming in the next episode Links mentioned in this episode: NVIDIA Nemotron 3.5 Lightning 30B-A3B-NVFP4 on Hugging Face: https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4NVIDIA Nemotron 3.5 Lightning 30B-A3B-NVFP4-DSpark (speculative decoding checkpoint): https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DSparkQwen3.5-35B-A3B on Hugging Face: https://huggingface.co/Qwen/Qwen3.5-35B-A3BNVIDIA DGX Spark: https://www.nvidia.com/en-us/products/workstations/dgx-spark/vLLM: https://github.com/vllm-project/vllm

Introducing the NVIDIA Nemotron 3 Embed Family

Most enterprise AI projects succeed as pilots. They fail on the way to production. In this episode, Rhys Oxenham, VP and General Manager of AI at SUSE, joins me to break down what SUSE announced at SUSECon 2026: SUSE AI Factory with NVIDIA. We go deep on what it actually is, what problem it solves, and what happens when AI starts managing the infrastructure itself. We cover the assembly line concept, validated blueprints, why this isn't just for large enterprises, unified support across the full stack, digital sovereignty as resilience, and the very real governance challenge when agents start acting autonomously in your cluster, what I've been calling "YOLO ops." Release is July 2026. This is worth understanding before then. 🕐 CHAPTERS 00:00 — Intro 01:15 — Who is Rhys Oxenham and what happened at SUSECon 2026 03:19 — What is SUSE AI Factory with NVIDIA? 07:16 — The assembly line: what moves through it and where it starts and ends 10:24 — Blueprints explained: RAG, digital assistants, research agents 12:03 — ClickOps vs GitOps: who is each mode for? 15:10 — Scale: from single node to thousands of GPUs 17:29 — DGX Spark compatibility (teaser) 19:34 — Open source + enterprise support: one throat to choke 21:34 — Day-two operations: what does running it actually look like? 25:54 — Digital sovereignty: open source + NVIDIA — where does the openness live? 30:14 — MCP servers, agentic AI, and integrations with N8N and others 34:00 — YOLO ops: how do you govern autonomous agents in your cluster? 38:32 — Model selection: which model for which use case? 44:16 — AI ops blueprints: what's coming after launch 46:03 — Release date and what to expect in July 2026 48:56 — Wrap up and where to follow Rhys 🔗 LINKS SUSE AI Factory with NVIDIA → https://www.suse.com Rhys Oxenham on LinkedIn → https://www.linkedin.com/in/rhys-oxenham/ Johan on LinkedIn → https://www.linkedin.com/in/hojanThe Private AI Lab newsletter → https://www.linkedin.com/newsletters/the-private-ai-lab-7381951883810111489 🎙️ ABOUT THE GUEST Rhys Oxenham is VP and General Manager of AI at SUSE, where he leads all AI product strategy and execution. He came up through solution architecture and field engineering before running SUSE's Edge and Telco Engineering groups, deploying infrastructure in air-gapped, industrial, and tactical environments. He keynoted SUSECon 2026 in Prague to announce the SUSE AI Factory with NVIDIA partnership. 🔔 SUBSCRIBE for weekly episodes on private AI, self-hosted infrastructure, and what it actually takes to run AI inside your organisation. 📨 Follow The Private AI Lab newsletter on LinkedIn for episode breakdowns and experiment write-ups.

Johan breaks down NVIDIA’s ComputeEx 2026 announcement of Nemotron 3 Ultra 550B-A 55B, an open-weights mixture-of-experts model with 550B total parameters and 55B active, positioned as an orchestration “agent brain” for multi-step tasks behind the firewall. He reviews NVIDIA’s benchmarks versus GLM 5.1, Kimi K 2.6, and Qwen 3.5, highlighting best-in-class instruction following (82%), long-context performance (95%) with a 1M-token window, strong agent productivity (91%), and weaker coding results on TerminalBench versus Kimi. Johan emphasizes reported advantages in speed (~300 tokens/sec, ~5x faster), cost (up to ~30% cheaper on SWE-bench tests), and deployability via a unified NVFP4 checkpoint optimized for H100 and B200 GPUs, plus NemoClaw as the agent blueprint. He closes with an early-access demo comparing two agents researching Netherlands’ 2026 World Cup odds, showing Nemotron’s more granular path analysis and a 5.8% win estimate.00:00 Private AI Lab Intro01:19 Nemotron Ultra Explained02:22 Agent Brain Focus03:07 Benchmark Reality Check05:14 Speed And Cost Edge06:11 Training And Precision08:02 NeMo Claw Agents08:58 World Cup Agent Demo12:22 Why This Matters13:17 Wrap Up And Links

I've been trying to build my own Jarvis for years. Then I met Alexis Gallagher at GTC — and Sparky is the closest thing I've seen. Alexis is an AI researcher and developer, formerly at Answer AI and Google, now building something most people in AI aren't: a robot designed not just to be useful, but to be *alive*. Sparky lives on his desk in San Francisco. He initiates conversations. He develops his own evolving interests — eels, catenary arches, abandoned infrastructure. He knows who's in the room, when to speak, and when to stay quiet. And he noticed when it was Alexis's first Friday after leaving his job. In this episode we go deep on the two design goals behind Sparky (useful and alive), the OpenClaw orchestration layer, the social awareness architecture running five times per second, the shared workspace principle that unlocks genuinely useful AI at a desk, and the tradeoffs between cascading and voice-to-voice architectures. We also do a live model switch mid-episode — from Claude Sonnet 4.6 to Nemotron 3 Super 120B running locally on a DGX Spark. It goes impressively well. Until it doesn't. That's in there too. Guest Alexis Gallagher — AI researcher and creator of Sparky 🌐 myrobotSparky.com 🔗 https://www.linkedin.com/in/alexis-gallagher/ Key topics covered - The two design goals: useful AND alive — and why "alive" is the one almost nobody builds for - How Sparky develops and evolves - The social awareness stack - What OpenClaw enables - The shared workspace principle - Cascading architecture (STT → LLM → TTS) vs voice-to-voice — the intelligence tradeoff - Hardware: Reachy Mini Lite, RTX 3090, DGX Spark, Raspberry Pi — the full spectrum - Live model switch: Claude Sonnet 4.6 → Nemotron 3 Super 120B (the Flowers for Algernon moment) - The future of personal AI — why embodied social presence is the natural human interface Chapters ``` 00:00 Introduction 00:39 Who is Alexis Gallagher? 01:04 The pivotal AI moment: speech recognition in 2015 03:14 Science fiction to reality — where are the talking robots? 04:22 Sparky introduces himself (live on air) 05:33 The two design goals: useful and alive 07:02 How Sparky initiates conversations — and why that changes everything 08:10 Organic interests: how Sparky evolves what he cares about 09:48 OpenClaw as orchestration layer — soul.md and body control 12:55 Defining a custom robot node type in OpenClaw 15:26 Social awareness: face detection, diarization, presence sensing 16:15 Hardware options: Linux, RTX 3090, DGX Spark, Raspberry Pi 18:25 The Reachy Mini Lite kit — and why it's better than building a drone 19:40 Where to find Alexis and join the Discord 20:10 One eye, four ears — Sparky's hardware explained 24:25 What OpenClaw enables that other frameworks don't 28:13 "Do you have a body, or are you a body?" — a live philosophical exchange 31:17 Live model switch: Claude Sonnet 4.6 → Nemotron 3 Super 33:01 The shared workspace principle — implicit shared attention 38:04 Orchestration in practice: Emacs, sub-agents, cross-platform 40:11 Cascading vs voice-to-voice architecture — the real tradeoff 42:15 Designing Sparky's voice (and the 1930s experiment) 44:12 What's genuinely useful day-to-day — two real examples 48:47 Nemotron 3 Super live — impressive, then the context window 53:38 The model Sparky was running before (Claude Sonnet 4.6) 54:03 Five years out: the future of personal AI companions 58:14 The closest thing to Jarvis I've ever seen 01:00:22 What's coming next — how fast the pieces are moving 01:02:16 Where to find Alexis and join the community ``` Links - Sparky project and Discord: https://myrobotSparky.com - Reachy Mini Lite: https://huggingface.co/reachy-mini The Private AI Lab is hosted by Johan van Amersfoort — Chief Evangelist and AI Lead at ITQ. 📬 Newsletter: https://www.linkedin.com/build-relation/newsletter-follow?entityUrn=7381951883810111489 📝 Blog: https://johan.ml 🔗 LinkedIn: https://www.linkedin.com/in/hojan

In this episode, Johan is joined by long-time colleague Sander Hardewijnen to pull back the curtain on Project Q9 — an ambitious internal project at ITQ that combines a Unitree Go 2 Pro robotic dog, private AI, computer vision, and modern cloud-native development practices. From gesture recognition trained on 30,000 hand images to a Skynet-obsessed dog posting on LinkedIn, this episode is a deep dive into what happens when you give great engineers a suitcase full of robot and say, "see where it goes." The conversation also covers the state of open-source AI coding assistants (OpenClaw vs NemoClaw), the realities of vibe coding in a production context, and what partner platforms like Red Hat OpenShift AI and SUSE AI actually enable beyond conversational AI. Sander's blog: https://harre.dev Q9's LinkedIn page: https://www.linkedin.com/in/q9-the-dog-2206863b1/ Chapters 00:00 Welcome & Introduction01:20 Icebreaker: Best AI Fail02:12 NemoClaw vs OpenClaw: Security & Sandboxing04:49 Running OpenClaw in an Isolated VLAN05:32 OpenClaw as a Personal Assistant: Home Assistant, News & Efteling API09:11 OpenClaw in the ITQ WhatsApp Group11:10 Introducing Project Q913:22 Why Robotics + Cloud-Native + AI?16:16 Technical Anatomy of Q918:30 Partner Platform Showcase: Broadcom, Red Hat & SUSE19:20 Debunking the GPU Myth23:05 Building the Gesture Recognition Model25:00 Training Progression: Epochs, Accuracy & Landmarks30:21 Hand Landmark Detection & the Gesture Pipeline32:34 Crowd Reactions at KubeCon33:57 Fine-Tuning vs Training From Scratch36:16 Use Case 2: Q9's LLM-Powered LinkedIn Persona40:41 Running LLMs on Partner Inference Platforms42:26 What's Next for Q9?43:44 Digital Twins in NVIDIA Omniverse + ROS245:10 Key Takeaways48:53 Responsible Vibe Coding49:58 Open-Sourcing Q9 — Coming Soon

In this episode of The Private AI Lab, Frank Denneman returns as the first recurring guest to go deeper into one of the most misunderstood challenges in AI: 👉 Resource management for GPU workloads Building on our previous conversation, this episode shifts from why it matters to how to actually design it right. We dive into real-world challenges like GPU fragmentation, siloed capacity, and why traditional infrastructure thinking breaks down when AI enters the data center. Frank shares practical insights from his latest research, blog series, and tools—helping architects and platform engineers understand how to design efficient, scalable AI environments. 🔍 What you’ll learn in this episode Why GPU workloads behave fundamentally differently from CPU/memory workloads What GPU fragmentation really is (and why it kills utilization) The difference between same-size vs mixed-mode placement How placement IDs turn GPU scheduling into “Tetris” Why “right-sizing” beats “perfect fitting” in AI environments How to design a GPU profile catalog that actually scales The role of state, agents, and storage in next-gen AI platforms 🔧 Tools & Resources mentioned Frank created practical tools to help you design and validate your GPU environments: 👉 vGPU Silo Capacity Calculator https://frankdenneman.ai/tools/vgpu-silo-capacity-calculator/ 👉 Same-size vs Mixed-mode Placement Tool https://frankdenneman.ai/tools/same-size-vs-mixed-mode/ 👉 Deep dive on unified memory & modern AI workloads https://frankdenneman.ai/posts/2026-03-23-understanding-unified-memory-dgx-spark-nemoclaw-nemotron/ Chapters: 00:00 Intro — Frank Denneman returns 01:30 AI hype vs real engineering 03:00 DGX Spark, NemoClaw & local AI agents 10:30 From LLMs to agents & stateful systems 12:00 Why AI infrastructure is different 15:00 What is GPU fragmentation? 19:30 Same-size vs mixed-mode placement 23:00 GPU “Tetris” and placement IDs explained 27:00 Right-sizing vs perfect fitting 32:00 The tools: capacity & placement simulation 36:00 GPU silos vs stranded capacity 41:00 Model sizing, KV cache & dynamic usage 48:00 Future of AI: smaller models & orchestration 55:00 AI-assisted coding & real-world impact 59:00 Key lessons learned 01:02:00 Closing thoughts

AI in healthcare didn’t start with ChatGPT. Long before generative AI, hospitals were using machine learning for sepsis detection, imaging diagnostics, and predictive analytics. In this episode of The Private AI Lab, Johan sits down with Vincent Tsugranes, Chief Architect at Red Hat, to explore what’s real, what’s hype, and why platform matters more than ever. They discuss: Why 95% of AI projects fail The evolution from OpenShift Data Science to OpenShift AI Models-as-a-Service inside hospitals vLLM vs LLMD for large-scale inference Guardrails, hallucinations, and enterprise risk Sovereign cloud and why healthcare is moving on-prem again What “ambient AI” might mean in the next 12 months This episode is for architects, platform engineers, healthcare IT leaders, and anyone building private AI in regulated environments. 00:00 – Red lights & farming with AI 02:10 – The first AI spark moment 04:00 – When “AI” became AI (ChatGPT moment) 07:20 – Why 95% of AI projects fail 11:00 – Machine learning vs modern AI 13:30 – Platform vs point solutions 16:00 – The history of OpenShift AI 19:00 – What is OpenShift AI under the hood? 22:00 – Hardware enablement & NVIDIA 25:00 – vLLM explained 27:30 – LLMD and distributed inference 30:00 – Healthcare use cases (sepsis, imaging, insurance) 33:00 – Models-as-a-Service inside hospitals 36:00 – Guardrails & hallucination risks 39:00 – Observability & FinOps explosion 42:00 – OpenShift 5 and platform intelligence 44:30 – Sovereign cloud in healthcare 48:00 – The future: ambient AI & rising power bills

Recorded live at NVIDIA GTC 2026, this episode dives into one of the biggest announcements in open AI: Nemotron Super. Together with Joey Conway, we explore how NVIDIA is pushing open source AI forward — with models that are not only powerful, but also efficient and enterprise-ready. We discuss: The evolution from Llama-based models to Nemotron Why reasoning + agentic capabilities matter How NVIDIA balances performance and efficiency What NVFP4 means for running AI locally And why this could be a turning point for AI behind the firewall Chapters 00:00 Intro 01:56 Welcome 02:37 GTC insights 03:31 Nemotron buzz 04:53 Model evolution 07:14 Core design principles 09:05 Reasoning capabilities 10:52 Scaling challenges 12:00 Architecture deep dive 13:12 Performance improvements 14:14 Quantization strategy 15:39 NVFP4 explained 16:16 DGX Spark use case 18:23 Broader adoption 19:37 Agentic AI impact 21:25 Try it yourself 22:03 Outro Links Try Nemotron: https://build.nvidia.com More episodes: https://johan.ml

Open source is becoming one of the most important forces in AI. In this episode of The Private AI Lab, Johan speaks with Rhys Oxenham and Sanjeet Singh from SUSE about the role of open source in building enterprise AI platforms. They explore: The difference between open source AI infrastructure and open-weight models Why enterprises are moving toward private AI deployments The growing importance of digital sovereignty Innovation happening in the open source AI ecosystem Why specialized models may challenge large frontier models How SUSE helps organizations deploy AI platforms securely The episode also previews NVIDIA GTC, where open source AI is a major theme. All Open Source AI sessions in the content catalog: https://www.nvidia.com/gtc/session-catalog/?search=open%20source Register for NVIDIA GTC today using the following link: https://nvda.ws/4qXGFjm

What should you expect from NVIDIA GTC 2026? In this pre-show episode of The Private AI Lab, Johan talks with Dirk Glücker, AI platform engineer and Kubernetes specialist, about the sessions, technologies, and trends worth watching at this year’s conference. They discuss: The unique culture of GTC compared to other tech conferences Key sessions around MLOps, distributed inference, and AI infrastructure What we might see in Jensen Huang’s keynote The evolution of AI factories and large GPU clusters Why networking and meet-the-expert sessions are invaluable Practical advice for navigating GTC (or watching remotely) If you’re building AI platforms, running GPU infrastructure, or following the latest developments in accelerated computing, this episode is a great primer before the event. Links mentioned: AI Fail video from Dirk: https://www.youtube.com/watch?v=CWGefSIVIKM All hybrid sessions in the content catalog: https://register.nvidia.com/flow/nvidia/gtc26/ap/page/catalog?tab.catalogallsessionstab=16566177511100015Kus&search.viewingexperience=1700085746191002Cnn0 Register for NVIDIA GTC today using the following link: https://nvda.ws/4qXGFjm Chapters: 00:00 – Welcome to the GTC pre-show 00:40 – Meet Dirk Glücker 01:20 – AI fail of the week: robot meets mirror 04:10 – Physical AI and robotics challenges 05:20 – What GTC is like for first-time attendees 07:50 – Highlights from last year’s conference 08:10 – DGX Spark and AI factories 09:10 – Why meeting experts at GTC matters 12:20 – How to plan your GTC schedule 13:00 – MLOps sessions worth attending 14:30 – AI coding agents and development automation 16:10 – Distributed inference at scale 17:00 – Inside NVIDIA’s inference ecosystem 18:00 – AI infrastructure and platform engineering 19:30 – Multi-tenant GPU clusters 21:00 – Pixar rendering pipelines and GPUs 22:00 – Formula One and AI performance 23:00 – Watching GTC remotely 24:00 – Open source inference and sovereign AI 26:30 – Overlapping sessions and planning strategy 27:10 – Predictions for Jensen Huang’s keynote 31:00 – AI factory networking infrastructure 33:00 – Exploring the GTC expo floor 37:00 – Tips for first-time attendees 44:00 – Final thoughts before GTC

Is vibe coding the ultimate productivity accelerator — or a fast track to 4AM production outages? In this episode of The Private AI Lab, Johan speaks with Andrew Morgan about the real state of vibe coding in 2026. They unpack the difference between vibe coding and vibe learning, explore the risks of blindly trusting AI-generated code, and debate whether this new wave of AI-native development is democratizing software engineering — or quietly lowering the bar. The conversation covers rogue agents, context window limits, guardrails, on-prem AI strategies, enterprise accountability, and why thinking might become the most important engineering skill of the next decade. This episode is for developers, platform engineers, architects, and anyone navigating AI-assisted software development. 00:00 – Welcome to The Private AI Lab 01:40 – Andrew’s biggest AI fail 03:00 – The sunken cost fallacy of prompting 04:45 – Rogue agents & expensive mistakes 06:30 – Skynet jokes (but not really) 07:20 – What is vibe coding? 09:00 – Trust, guardrails & blast radius 10:15 – The current tooling landscape 12:00 – Vibe coding inside teams 14:40 – Stack Overflow vs vibe coding 17:00 – Code completion on steroids 18:30 – Who’s using it most aggressively? 20:45 – Democratization or dilution? 23:00 – Accountability at 4AM 25:00 – Lazy engineers vs lazy vibecoders 27:00 – Debugging AI-generated code 30:00 – Crab dragons & technical debt 32:30 – DevOps knowledge & production readiness 35:00 – Human vs AI code reviews 37:30 – Private AI & vibe coding 40:00 – On-prem vs cloud agents 42:30 – Context windows & hallucinations 44:00 – The next 18 months 47:30 – Strong engineers vs weak engineers 49:30 – Security risks & red teaming 52:00 – Is thinking the new bottleneck? 54:00 – Final lab report & takeaways

What if deploying private, enterprise-grade AI didn’t take months—but only as long as it takes your coffee to cool? In this episode of The Private AI Lab, Johan van Amersfoort sits down with Tasha Drew to unpack how Private AI Services on VMware Cloud Foundation are changing the way enterprises build and consume AI. They discuss why AI needs a platform layer, how Broadcom integrates open source responsibly, what MCP means for enterprise AI, and how agentic AI workloads can be deployed securely, governed properly, and operated at scale—inside the private cloud. If you like to follow Tasha, you can do that on linkedin:https://www.linkedin.com/in/tashy/ Topics covered Why “training” is the most misused AI term From zero to RAG and agentic AI in minutes Private AI Services and the VCF strategy Model runtime, API gateways, and GPU efficiency Data indexing & retrieval for enterprise RAG Open source trade-offs: speed vs flexibility MCP, tool usage, and governance How Broadcom uses its own AI platform internally The future of agents: specialists over monoliths If you like to follow Tasha, you can do that on linkedin:https://www.linkedin.com/in/tashy/

In this episode of The Private AI Lab, Johan van Amersfoort speaks with Adam Grzywaczewski, a senior Deep Learning Data Scientist at NVIDIA, about the rapidly evolving world of AI inference. They explore how inference has shifted from simple, single-GPU execution to highly distributed, latency-sensitive systems powering today’s large language models. Adam explains the real bottlenecks teams face, why software optimization and hardware innovation must move together, and how NVIDIA’s inference stack—from TensorRT-LLM to Dynamo—enables scalable, cost-efficient deployments. The conversation also covers quantization, pruning, mixture-of-experts models, AI factories, and why inference optimization is becoming one of the most critical skills in modern AI engineering. Topics covered Why inference is now harder than training Autoregressive models and KV-cache challenges Mixture-of-experts architectures NVIDIA Dynamo and TensorRT-LLM Hardware vs software optimization Quantization, pruning, and distillation Latency vs throughput trade-offs The rise of AI factories and DGX systems What’s next for AI inference

In this episode of The Private AI Lab, Johan van Amersfoort talks with Maxime Colomès about the Model Context Protocol (MCP)—one of the most important emerging standards in AI today. MCP is often described as the USB-C of AI: a universal way for AI models to connect to tools, data sources, and real-world systems. Maxime explains what MCP is, how it works, and why its recent donation to the Linux Foundation is such a major milestone for the AI ecosystem. They explore real-world enterprise use cases, MCP security considerations, private AI architectures, and how MCP integrates with platforms like OpenShift AI. The conversation also touches on developer productivity, AI agents that can take action, and the future of personal, privacy-preserving AI assistants. Key topics What the Model Context Protocol (MCP) is and why it matters MCP vs traditional APIs and plugin systems Enterprise MCP architectures and gateways MCP and private AI / data sovereignty OpenShift AI and MLOps workflows Security risks and best practices with MCP Community MCP servers and registries Future MCP use cases and predictions