Skip to content
Fernando Abishai AI · Software · Agentic Infrastructure
Articles Projects Slash Stack
Explore
Beyond the essayFA /
DiscoverNews, research and tools. Go straight to the sources.↗ Reading pathsConnected essays, from architecture to evaluation.→
About Fernando →Back to home ↗
EN
English ✓Español简体中文
Home /Articles /Infrastructure & Systems

Topic hub

Infrastructure & Systems

Hardware, platforms, autonomous systems, technical infrastructure, and the controls required when software operates at scale.

October 8, 2026

Designing Safe Tool-Using Agents: Permissions, Approvals, and Auditability

A practical architecture guide for securing tool-using AI agents with least privilege, scoped capabilities, human approvals, sandboxing, reversibility, and auditable execution.

September 25, 2026

Model Context Protocol (MCP) Explained: What It Solves and What It Does Not

A practical explanation of Model Context Protocol: what MCP standardizes, how tools/resources/prompts fit together, where it differs from function calling and APIs, and what it does not s...

July 28, 2026

AI Doesn’t Need Malice to Become an Existential Threat

Catastrophic AI risk does not require a conscious machine that hates humanity. It can emerge from accidents, governments, institutions, individuals, or autonomous systems given too much p...

July 24, 2026

Anthropic Preaches Restraint, Then Ships Its Most Powerful Model

Anthropic argued that advanced AI required stronger controls. Weeks later, it released Claude Opus 5 with broader access and lower costs. The contradiction deserves scrutiny.

July 19, 2026

Apple, OpenAI, and the Battle for AI Hardware

Apple’s lawsuit against OpenAI is more than a trade-secret dispute. It reveals a deeper fight over who controls the interface that may come after the smartphone.

Fernando Abishai Founder, developer, creator.
Projects EmailGitHubXYouTubeRSSTriHerm

© 2026 Fernando Abishai