Month: October 2026

  • When AI Gets Too Helpful: Preventing Data Exfiltration by Unbounded Agents

    A very long time ago, I was the Thought Police. I worked at a credit union data center, and I was one of the IT administrators. One of the rather unpleasant tasks I had was to monitor the Microsoft Exchange email server for sensitive data like account numbers, credit card numbers, OFAC data, etc. Microsoft…

    Continue reading →

  • You Ask, I Answer: Mapping Business Processes for AI Agents?

    Summary In today's episode, I walk through how to map and document undocumented business processes so AI agents can understand and execute them using Trust Insights' 5P framework. Here's what this means for you. You'll gain a structured way to translate the tacit knowledge trapped inside your senior staff's heads into agent-ready instructions without losing…

    Continue reading →

  • Why Always-On AI Agents Are a Resource Nightmare: The True Cost of Meta Muse and Token Waste

    “It’s your always-on assistant”. This is the common refrain for all the new agent harnesses – Meta Muse, OpenAI Dots, etc. And it’s terrible. Here’s why: an always-on agent is, well, always on. That means it’s always consuming resources in some fashion, whether or not you want it to be. For example, I use Hermes…

    Continue reading →

  • So What? What’s New with the LinkedIn Algorithm?

    Summary In today's episode, I break down what's new in the fifth edition of the LinkedIn Algorithm Guide from Trust Insights and explain how LinkedIn's ranking system really works. Here's what this means for you. You gain a clear picture of how two separate language models decide which posts reach you and what specific levers…

    Continue reading →