Most of a makelaar's time isn't selling houses
The tools already do useful work. The question is what still depends on a person to carry context, resolve exceptions and close the loop.
Read moreNotes on agentic operating systems, sovereign architecture, and building software that respects how regulated firms actually have to work.
The tools already do useful work. The question is what still depends on a person to carry context, resolve exceptions and close the loop.
Read moreFollow a client proposal through coordinating agents, checking progress and improving results, then decide what your firm wants to build and run.
Read moreIn a small design agency, proposals, coordination and sign-off chasing eat the senior people. What an agentic operating system takes off them.
Read moreA practical guide for professional-services leaders to fix outcomes, workflows, permissions, evaluation, and ownership before scaling an AI agent.
Read moreAI can produce more software, more quickly. The advantage is moving to teams that understand what should be built, how work should change, and where human judgement must remain.
Read moreWhat happened when I tried to scale a four-person software company with AI agents.
Read moreClaude Tag made it easier to bring agents into team workflows. The next question is what those agents can see, touch, remember, and escalate.
Read moreWhy 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 moreSingle agent vs multi-agent: when to clone an agent versus define a new one - and the four factors that decide.
Read moreYou'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 moreEvery engagement begins with a conversation about what you're running today and what the right next step looks like.