Mike Hogan

@GarryTan, President of Y Combinator, recently delivered a compelling vision for the future of work in AI-native organizations. He explains agentic workflows using a straightforward and powerful analogy: treat AI agents like human employees in a growing company. You hire them, train them, manage the...

As more agents go into production, agent reliability has surfaced as a serious issue that requires immediate attention. Here’s your “easy button” solution. Trustabl is a static analyzer that scans agent repos built on Claude, OpenAI, Google ADK, and MCP and finds reliability and safety issues ...

The AI talent market feels lopsided right now. Companies have uncapped budgets and still can't find enough people who can actually deliver. Training programs are everywhere. Yet a real gap persists between what most courses teach and what teams are hiring for. The difference often comes down to arti...

A new paper from Queen’s University researchers didn’t just theorize about flaky AI agents. They measured it. They analyzed 856 tools across 103 real MCP servers (both official ones from big names and community-built ones). Using a structured rubric and an FM-based scanner, they found that 97.1%...

AI agents are getting more powerful by the month. At the same time, many teams are watching their token bills climb and their context windows fill up faster than expected. The problem is rarely the model itself. A significant contributor to token waste is how tools are described and how agents decid...