Devops Blog – Openstack, Openshift,- Docker, Kubernetes, Swarm, Linux, Windows Stacks – Mongodb, An occasional opinion
The 9 Security Tools I Wired Into Agent Provost’s CI Pipeline (And Why Most AI Projects Have Zero) After 20+ years in DevOps, I’ve seen a lot of “secure” pipelines. Most of them aren’t. They lint. Maybe they run a container scan. That’s it. Now that AI agents are executing real trades through APIs like …
After weeks of researching the AI trading landscape, talking to Chief Risk Officers, and analyzing how builders are using LLMs, one thing is clear: Everyone is moving to LLM-based trading. And nobody has the governance layer to do it safely. The New Trading Workflow The way people trade has changed! The old way: staring at …
Continue reading “The Execution Gap: Why AI Trading Needs a New Kind of Governance”
The “Detective” Boot: Breaking Through the Kafkaesque Gatekeepers of AWS AMIs In Franz Kafka’s parable “Before the Law,” a man spends his entire life waiting for a gatekeeper to grant him entry to the Law. He dies waiting for permission that was technically already his. I’ve lived this Kafkaesque nightmare at multiple companies, watching remote, …
Continue reading “Stateless AWS AMIs: How to Build a Reboot-Persistent “Detective” Boot”
I’ve seen this exact movie play out at three different tech companies: Me: “I can handle our AWS Marketplace deployment. I’ve done it before.” Management: “That’s fine, Sales will figure out the Marketplace stuff.” Fast forward six months. The product never went live on the Marketplace until the company hit the layoff phase, and we …
Continue reading “1-Click Enterprise Deployments: Engineering Agent Provost for AWS Marketplace”
When I hire new developers (different Coding Agents) , I do not assume perfect behavior. I assume velocity, curiosity, and occasional mistakes. So I designed Agent Provost around one non-negotiable product boundary: The product is the audit log format. If that format drifts, we lose chain-of-custody, investigations get harder, and trust disappears. Everything else is …
Continue reading “How We Made Agent Provost Hard to Break as We Scale the Team”
Safety and Governance As enterprises rush to deploy autonomous AI agents, the critical missing piece has been robust AI governance and security. Without strict guardrails, an LLM with API access is a ticking compliance time bomb. This is the story of how one visionary architect, Steven Craig Bar Yakov Gindi, recognized this massive vulnerability and …
Continue reading “11 Days That Changed AI Agent Safety Forever”
By a Senior DevOps Engineer who thought nginx would be enough. The Problem Nobody Is Talking About AI trading agents are going live. Right now. Not in some distant future — today, LLMs are executing real trades through APIs like Alpaca, making decisions at machine speed, and holding accountability to exactly nobody. I’ve spent years …
Building a Two-Way MITM Audit Ledger for AI Agents The Mission: A Tamper-Proof System of Record AI agents are unpredictable. When an agent interacts with a financial API like Alpaca.markets, you need more than just a “feeling” that it’s working—you need an immutable, two-way audit trail. I set out on a learning adventure to build …
Continue reading “Deep Dive: Real-World Logging and Tool Calls in the Agent Provost Project”
AI Agents Are Powerful — and Sometimes Completely Out of Control After more than twenty years in DevOps and infrastructure engineering, I’m used to systems failing in predictable ways. Hardware dies. Networks flap. Someone forgets to rotate a token. Fine. But AI agents? They fail in ways that make you stop and wonder how anyone …
During an Interview as a Senior Devops, My Apple Watch said “Buzz buzz, your hearts racing! Are you OK? Should I text your son and wife ?” The interview might have been successful and I might continue the process, I might have been correct for an important security question that they claimed I was mistaken! …
Continue reading “The Racing Heart and Tongue Tied Devops Interview”
LLMs do not take into account the entirety of a project LLMs struggle with real-world deployments, consistently forgetting ~20% of critical components. This became clear while setting up @Istio on Kubernetes with Prometheus and Kiali observability. Following my thoughts on DevOps interviews and whiteboard coding tests (see link below), I’m now seeing the flip side …
Continue reading “Navigating the Challenges of LLMs in Real-World DevOps Deployments”
Developer Hiring Managers that dont understand Devops As a DevOps engineer with over 20 years of experience I recently faced an interviewer who was genuinely shocked that I couldn’t find the missing number in an array of 1 to 100. Yes, really. This happened in 2025, when GitHub Copilot could solve this in seconds. Let’s …
Continue reading “Devops interview Paradox: When Whiteboard Hazing Replaces Real Skills”
I was recently on the job search Market in Tel Aviv and Jerusalem seeking a job as a Senior Devops. I found a great job At Coro Cybersecurity Another company whose name I do not remember. I do remember that it was high floor and had a great play room for kids! They gave me …