Agentic AI is moving faster than enterprise readiness.

Boards are pushing adoption. Teams are deploying agents at speed. But security, control, and operational discipline are lagging behind.

In this episode, Mehmet sits down with Craig McLuckie, the co-creator of Kubernetes and founder of Stacklok, to unpack why most agentic AI initiatives break after the demo and what enterprises must do differently to make them durable, secure, and production-ready.

From MCP and context engineering to eval-driven development and why AI agents should never be treated like interns, this conversation goes deep into the realities CTOs, VPs of Engineering, and security leaders are facing right now.

This is not a hype conversation. It’s an operator’s reality check for 2026.

⸻

👤 About the Guest

Craig McLuckie is a foundational figure in modern cloud infrastructure. He is the co-creator of Kubernetes, founder of the Cloud Native Computing Foundation, and former VMware executive behind the Tanzu portfolio.

Today, Craig is the founder and CEO of Stacklok, where he is focused on helping enterprises securely connect agentic AI systems to real-world infrastructure through open, controlled, and auditable platforms.

https://www.linkedin.com/in/craigmcluckie/

⸻

🧠 Key Takeaways

• Why agentic AI represents a true epoch shift, not just another tooling cycle

• The real difference between demos, POCs, and production AI systems

• Why MCP is powerful but dangerous without proper control layers

• How context engineering is becoming more important than writing code

• Why eval-driven development replaces test-driven development in AI systems

• How enterprises should think about permissions, scope, and agent autonomy

• Why most AI failures are workflow problems, not model problems

• What 2026 realistically looks like for agentic AI adoption in the enterprise

⸻

🎯 What You’ll Learn

• How to operationalize agentic AI without exposing your infrastructure

• Why treating AI agents like humans is a security mistake

• How to design guardrails without slowing teams down

• Where CTOs should focus investment to move from hype to ROI

• How leadership metrics and engineering evaluation must evolve in the AI era

⸻

⏱ Episode Highlights & Timestamps

• 00:00 – Introduction and Craig’s journey from Google to Kubernetes

• 03:10 – Why agentic AI feels like a historic inflection point

• 06:05 – MCP explained and where enterprises get it wrong

• 10:45 – The security risks nobody is talking about

• 14:20 – Why AI agents should never be treated like interns

• 18:30 – The danger of permission sprawl and tool pollution

• 23:10 – Why most AI initiatives fail after the demo

• 28:40 – Eval-driven development vs traditional software thinking

• 34:15 – Context engineering as the new leverage point

• 38:50 – How engineering leadership and metrics must change

• 43:30 – What realistic agent adoption looks like in 2026

• 46:20 – Open source, ToolHive, and building durable AI platforms

⸻

🔗 Resources Mentioned

• Stacklok: http://stacklok.com/

• ToolHive (Open Source MCP Platform): https://stacklok.com/toolhive/

In this episode, Mehmet sits down with Ghazenfer Mansoor, Founder and CEO of Technology Rivers, to unpack why so many software products fail quietly and what actually separates ideas that ship and scale from those that die early.

Drawing on two decades of experience and over 60 shipped applications, Ghazenfer shares hard-earned lessons on customer discovery, feature bloat, technical debt, AI with real ROI, and building system-powered businesses that scale sustainably, especially in regulated industries like healthcare.

This is a practical, no-fluff conversation for founders, CTOs, and operators building real products in a noisy AI-driven world.

⸻

👤 About the Guest

Ghazenfer Mansoor is the Founder and CEO of Technology Rivers, a custom software development company with deep expertise in healthcare, HIPAA-compliant systems, and AI-driven operational automation.

He began his career as an early startup engineer, entered mobile development in its earliest days, and has since helped build and scale dozens of products. Ghazenfer is also the author of the upcoming book Beyond the Download, focused on building mobile apps people actually love and use.

https://www.linkedin.com/in/gmansoor/

⸻

🧠 Key Takeaways

• Why most startups fail by building solutions before validating problems

• How feature bloat quietly destroys velocity, quality, and scalability

• The hidden cost of technical debt and why postponing it always backfires

• Why AI tools fail without clean data and mapped workflows

• How regulated industries can innovate without breaking compliance

• The shift from people-powered growth to system-powered growth

• Why founders should think like acquirers from day one

⸻

🎯 What You’ll Learn

• How to identify the real problem worth solving before writing code

• How to prioritize features without killing your product roadmap

• Where AI delivers real ROI versus where it’s just pitch-deck noise

• How to design internal systems that create defensibility and valuation

• Why compliance and innovation are not opposites

• How to build products that users return to, not just download

⸻

⏱️ Episode Highlights & Timestamps

• 00:02 Ghazenfer’s journey from early mobile engineering to healthcare software

• 05:10 Why most startup ideas fail before reaching scale

• 08:00 Feature race vs focus and why more features hurt products

• 10:15 Technical debt explained in simple, practical terms

• 14:00 AI in practice vs AI in pitch decks

• 17:30 Why workflows matter more than tools

• 19:45 Innovating in healthcare without breaking HIPAA

• 23:00 RAG, hallucinations, and building safe AI systems

• 26:45 Beyond the Download and building retention-first products

• 35:30 Moving from people power to system power growth

• 41:00 Thinking like an acquirer from day one

• 46:00 Final advice on AI, innovation, and staying relevant

⸻

📚 Resources Mentioned

• Technology Rivers https://technologyrivers.com/

• Beyond the Download by Ghazenfer Mansoor: https://technologyrivers.com/l/beyond-the-download/

• HIPAA compliance principles

• Retrieval-Augmented Generation (RAG) architectures

• AI tools including Claude, ChatGPT, and Gemini

In this episode of The CTO Show with Mehmet, Mehmet sits down with Michael Ferranti, a seasoned tech executive and product leader at Unleash, to explore why DevOps alone can no longer meet the reliability, speed, and risk demands of modern software systems.

From real-world outages at Google and Cloudflare to the rise of AI-driven delivery, this conversation introduces FeatureOps as the missing control plane that allows teams to move faster without breaking production.

⸻

👤 About the Guest

Michael Ferranti is a tech executive with over a decade of experience across DevOps tooling, infrastructure software, open source, and enterprise platforms. He has played key roles in scaling developer-focused technologies and advises organizations on balancing innovation, reliability, and governance at scale. Today, he focuses on FeatureOps as a foundational capability for modern engineering teams.

⸻

🧠 Key Takeaways

• DevOps optimizes deployment, but FeatureOps governs runtime behavior

• Many large-scale outages are caused by “big bang” releases without kill switches

• Feature flags are not just for UI experiments, they are safety mechanisms

• FeatureOps enables faster shipping and lower risk at the same time

• AI-driven engineering increases the need for runtime control, not less

⸻

🎯 What You’ll Learn

• Why DevOps alone breaks down at scale

• How FeatureOps differs from traditional feature flagging

• Lessons from Google and Cloudflare outages

• When open source helps and when it complicates GTM

• How AI changes release management and reliability decisions

• Why human-in-the-loop control still matters in autonomous systems

⸻

⏱️ Episode Highlights & Timestamps

• 00:02 – Michael’s journey from early cloud evangelism to FeatureOps

• 04:00 – Scaling Portworx and why technology alone is not enough

• 07:30 – Open source as a GTM strategy, myths and realities

• 15:00 – Kubernetes, scale assumptions, and overengineering traps

• 21:30 – What FeatureOps actually is and why it matters

• 24:30 – Google outage case study and the cost of big bang releases

• 27:30 – Cloudflare, kill switches, and runtime control

• 31:00 – FeatureOps vs DevOps explained clearly

• 35:00 – AI in release decisions and risk management

• 43:00 – Human-in-the-loop engineering and future architectures

⸻

🔗 Resources Mentioned

• Unleash Feature Management Platform: https://www.getunleash.io/

• Google SRE Handbook

• DORA Reports on High-Performing Engineering Teams

• ThoughtWorks Feature Management Practices

⸻

🔗 Connect with the Guest

• Michael Ferranti on LinkedIn: https://www.linkedin.com/in/ferrantim/