Making Lemonade
What happened when I tried to scale a four-person software company with AI agents.
Read moreBlog
Notes on agentic operating systems, sovereign architecture, and building software that respects how regulated firms actually have to work.
Claude Tag, Open Tag, Why The Tag is Only The Beginning
Claude Tag made it easier to bring agents into team workflows. The next question is what those agents can see, touch, remember, and escalate.
Read more
Your Firm May Not Need Another AI Agent. It Needs An Operating Layer: Agentic-OS
Why isolated AI agents stall, what an Agentic-OS adds, and how context, tools, permissions, review, memory, measurement, and governance turn AI into work the firm can trust.
Read more
How Many AI Agents Do You Actually Need?
Single agent vs multi-agent: when to clone an agent versus define a new one - and the four factors that decide.
Read more
Most firms have agents, not an operating system
You've tried AI and hit a wall. The problem isn't more AI — it's the agentic operating system your firm doesn't have yet.
Read moreWant to talk about your own agentic system?
Every engagement begins with a conversation about what you're running today and what the right next step looks like.