Sign in Subscribe

Stephen Young

Stephen Young

Steve is founder and CTO at FactNexus and architect of multiple complex-data-based applications - including the CAT3 AI governance platform.

📍 Sydney, Australia https://factnexus.com

Tool-Using AI Agents - Balancing Competence, Competition and Risk

Tool-using AI agents capable of interacting with well-constructed APIs already exist. In this article we examine how these agents are likely to evolve, the tension between competitive speed and governance risk, and the emerging role of standards like MCP and A2A.

A Good AI Agent is a Tested AI Agent

If your AI agent isn't comprehensively tested, it can’t be trusted.

Beyond the Knowledge Base: How Good AI Agents Piece Together the Truth

Enterprise data is siloed, scattered, secured, stale, and often conflicting. A simple retrieval-augmented generation (RAG) pipeline breaks easily in this world. AGENTIC RAG , however, is designed to adapt.

The Rise of Agentic AI Coding Tools

Google has just launched Firebase Studio, an AI-powered development environment that lets you build entire apps from a prompt. It's part of a growing class of agentic AI coding platforms—systems that don’t just assist with code - they reason about, plan changes and even execute them.

AI as a Habit. Financial Value as a Goal.

Tobias Lütke, CEO of Shopify, recently shared a company-wide directive: “Reflexive AI usage is now a baseline expectation at Shopify.” It’s a powerful idea —but reflexive AI use alone won’t guarantee value.

Good Agents Are Sustainable: What Multi-Agent AI Can Learn from Microservices

When enterprises first embraced microservices, they were chasing agility. They wanted to move fast, scale smart, and avoid the brittle overhead of monolithic applications. They quickly discovered, however, that speed without structure leads to fragility. The same is true for AI agents.

Vibe-Coded US Tariffs: Why There Needs to Be a SMART Human in the Loop

When commentary emerged today suggesting that the White House had used a ChatGPT formula to set international tariffs, people thought it must have been a late April Fools Day joke.

Looks Smart, Gets It Wrong: Hallucination and AI Agents

Generative AI is impressive — but it makes things up more often than most of us realize.

MCP and the AI Governance Gap: A Wake-Up Call for Enterprise

Anthropic's Model Context Protocol (MCP) is gaining significant attention in the AI community. But is it pushing some important governance issues into the background?

AI as a Teammate? A Groundbreaking Study Says Yes—And It’s Surprisingly Human

If AI agents are going to fit into our workplace, they need to do more than just perform—they need to collaborate, communicate, and connect —like good teammates.