Beyond Prompt Injection: The Hidden Trust Problem in Enterprise Agentic AI

Publications Date Length 5+ min read Beyond Prompt Injection: The Hidden Trust Problem in Enterprise Agentic AI Categories: Author Ian van Eenennaam Linkedin Introduction Imagine giving a highly capable junior operator a stack of meeting notes, tickets, design docs, and pull requests, then asking for a recommendation. Now imagine that somewhere in that stack, mixed […]

Exploring GPT-5: Generating a Website with a Single Prompt

Publications Date Length 3 min read Exploring GPT-5 Generating a Website with a Single Prompt Categories: Author Ian van Eenennaam Linkedin Introduction We’ve started testing the capabilities of the newly released GPT-5 API in the OpenAI Playground — and the results are nothing short of impressive. In our early experiments, we focused on a simple […]

Defining Interpretable and Generalizable AI Agent Behavior

Publications Date Length 10 min read Defining Interpretable and Generalizable AI Agent Behavior Categories: Author Ian van Eenennaam Linkedin Introduction Artificial Intelligence (AI) systems are increasingly becoming integral to various aspects of modern life, from healthcare and finance to transportation and communication. As these systems take on more critical roles, ensuring their behavior is both […]