The Agentic Engineering Platform: You Have a Coding Agent. Now What?
Use a governed agent harness to superpower the full spectrum of engineering work.
Agentic AIPlatform EngineeringZero Trust
Original writing on Zero Trust, governed autonomy and the architecture between them. Lessons from designing, building and operating real systems.
Use a governed agent harness to superpower the full spectrum of engineering work.
Agentic AIPlatform EngineeringZero Trust
Zero TrustNetwork as a ServiceSecurity ArchitectureEnterprise Security
North-South is the door. East-West is the hallways. Network as a Service is the floor they are both standing on - and, on the worst day, the net beneath them. The least glamorous layer in the stack is the most load-bearing.
Zero TrustMicrosegmentationSecurity ArchitectureAgentic AI
One camp secures the network you already have. The other decides the network should not exist unless you are allowed to see it. You would love to run both. Most enterprises will not.
Agentic AIZero TrustAI GovernanceSpec-Driven DevelopmentAgentic Coding
Spec-driven development paired with the right harness turns an autonomous coding agent into a production powerhouse. Drop that setup into a regulated enterprise without governance and the security team will shut it down in five minutes - and they would be right to do so. Here is the control plane that makes agentic coding safe at enterprise scale.
Agentic AISpec-Driven DevelopmentAgentic CodingSoftware Engineering
Two months ago I published a 542-line spec and said 'the code is a side effect.' The spec is now 4,400 lines. The code is over 100,000 lines. Here's what happened when the spec stopped being a document and became the product.
Zero TrustSecurity ArchitectureEnterprise Security
Zero Trust was never just a security initiative. It was an architectural bet - and the companies that made it early are about to collect.
Zero TrustSecurity ArchitectureEnterprise Security
Everyone saw the architecture. Nobody saw the evaluation behind it. We read every major analyst report. Then built a framework that disagreed with all of them.
Agentic AISpec-Driven DevelopmentAgentic CodingSoftware Engineering
Everyone's talking about AI writing code. Almost nobody's talking about why most of it ends up in the trash. ~70,000 lines of code later, I accidentally built my favorite development environment.
Zero TrustSecurity ArchitectureEnterprise Security
How do you bring Zero Trust to an organization that is older than the concept of a computer? Architecting the transition felt like changing the engines on a plane mid-flight - while that plane was carrying the entire population of a nation.
Agentic AIGraduated AutonomyAI GovernanceZero TrustSecurity Architecture
I put a small AI model in charge of my firewall. Then I hired a larger model to watch it. Not just to save time - but because humans are no longer fast enough to stop machine-led attacks.
Agentic AIAI GovernanceGraduated AutonomyZero TrustSecurity Architecture
Something is shifting in how we build and protect systems. The center of gravity is moving - from writing logic to managing systems that generate it. What hit development is about to hit security. Are you ready?
Zero TrustAI SecuritySecurity Architecture
The era of the static security rule is ending. As modern organisations roll out new infrastructure on edge platforms, a pattern is emerging that deserves more attention: legacy security components are getting smarter.
Contact
Whether you need a Zero Trust assessment, an AI governance architecture, guidance on agentic coding adoption, or help selecting the right technology - I'm here to help. Direct conversation with the architect who does the work.
Agent-readable document
/blog/
Markdown view