Elvatis Blueprint

Sign in Subscribe

90 Days Solo With AI Agents: A Field Report on What Holds Up Under Load

90 Days Solo With AI Agents: A Field Report on What Holds Up Under Load

Ninety days running a portfolio with AI agents as the primary execution layer. The patterns that held up, the patterns that broke, and the operating discipline the speed demands.

🛡️ Fortinet Monthly Recap | April 2026

🛡️ Fortinet Monthly Recap | April 2026

Monthly Overview April 2026.

When the AI Does It Before You Ask: A Week With Autonomous Agents

When the AI Does It Before You Ask: A Week With Autonomous Agents

I spent a week running parallel AI agent workflows with self-healing, CLI routing, and automated tasks. Here is what actually happened.

🛡️ Fortinet Monthly Recap | March 2026

🛡️ Fortinet Monthly Recap | March 2026

Monthly Overview March 2026.

I scanned the leaked Claude Code source before building it

I scanned the leaked Claude Code source before building it

I scanned a widely-shared copy of leaked Claude Code source before running it. The scanner returned a critical score. Here is what the findings actually mean, and why the repository distributing it deleted my comments.

Introducing elvatis-mcp: Control Your Entire Infrastructure from Claude Desktop

Introducing elvatis-mcp: Control Your Entire Infrastructure from Claude Desktop

A new open-source MCP server that connects Claude, Cursor, and Windsurf to your smart home, memory, cron jobs, notifications, and local LLMs - with 32 tools across 7 domains.

How We Swept 25 Repos for Security Issues in an Afternoon (and What We Actually Found)

How We Swept 25 Repos for Security Issues in an Afternoon (and What We Actually Found)

A practitioner's account of running a full Dependabot and CodeQL sweep across an entire GitHub organization, fixing real vulnerabilities, and hardening a production server the same day.

NIS2 for Mid-Sized Companies: What Actually Matters

NIS2 for Mid-Sized Companies: What Actually Matters

NIS2 is here and most mid-sized companies don't know if they're affected. Here's a practical checklist from someone who's been through TISAX.

How GlassWorm Gets In (and How We Locked It Out)

How GlassWorm Gets In (and How We Locked It Out)

A supply-chain malware campaign hit hundreds of repos across GitHub, npm, and VS Code. Here's what I found when I scanned my own projects.

Two Bugs, One Sunday Morning: What Debugging Your AI Gateway Actually Teaches You

Two Bugs, One Sunday Morning: What Debugging Your AI Gateway Actually Teaches You

A plugin crash and a process fork bomb walked into a Sunday. What I learned about tool schemas, token limits, and why reading vendor specs matters.

Who's Responsible When AI Breaks the Rules It Wrote Itself?

Who's Responsible When AI Breaks the Rules It Wrote Itself?

Here's something that should make you uncomfortable.

Human-in-the-loop: Why Autonomy Should Not Be All or Nothing

Human-in-the-loop: Why Autonomy Should Not Be All or Nothing

I woke up at 2:30 a.m. replaying the same question: what does autonomy really mean when you are the one who still has to clean up the mess.