Articles

Operator notes.

Problem-first writing on AI, automation, and the process underneath. Each piece names a real bottleneck, exposes the broken layer nobody owns, and shows what the working system actually looks like.

Enterprise AI

Integration and data contracts: the layer that decides whether AI agents work

The 2026 protocol wave (MCP, A2A) connected agents to your systems. It didn't make your systems agree. Why integration and data contracts decide whether enterprise AI works.

5 min read →
Healthcare admin

The AI opportunity in healthcare isn't in the chart. It's in prior authorization.

Prior authorization automation is a process problem, not an AI one. The bottleneck is the admin layer — fax queues, payer PDFs, manual handoffs — not the clinical model.

4 min read →
Logistics & freight

When a carrier exposes its automation stack as an API, the failure mode moves

Amazon-grade logistics automation is becoming reachable by API. The catch: an automation-first network won't tolerate messy data. Automating shipment status updates starts with the prep layer nobody wants to own.

4 min read →
Enterprise AI

Multi-agent orchestration won't fix a process that's already broken

Orchestration assumes the handoff underneath is clean. Usually it isn't. Why most multi-agent AI projects fail at the seam, and what to fix before you add a second agent.

4 min read →
AI governance

Shadow AI isn't a policy gap. It's an inventory gap.

Most enterprise AI runs outside any governance. You can't govern what you can't see — shadow AI is an inventory problem first, a policy problem second. What an operator-grade containment layer looks like.

4 min read →
Optimization / OR

The utility scheduler no off-the-shelf product could build

A custom constraint-optimization engine hit 96% workday efficiency on more than a dozen interacting constraints. When scheduling software stops fitting, the answer is operations research, not another SaaS subscription.

5 min read →