Alex J Jemmy

By now, most of you have seen the news.

A cluster of hantavirus cases has emerged aboard the Dutch cruise ship MV Hondius. As of this week, five confirmed cases, three deaths, and roughly 150 passengers are still on board while governments argue over where the ship is allowed to dock. Passengers from 23 nationalities are on that vessel. Three people have already died. This is a real, unfolding public health event, and our thoughts are with everyone affected.

We don't want to minimize that. People are scared. That's understandable.

But fear, especially online, has a shadow. And that shadow, predictably, is The Simpsons.

There's a pattern I keep noticing across the AI products that actually stick with people vs. the ones that get tried once and forgotten.

The forgettable ones try to be impressive. They show off what the model can do -- generate faster, automate more, produce output at scale. And they're genuinely cool for about 15 minutes.

We've been getting the same request over and over from our users: "My AI gives great answers, but it can't actually do anything."

It got us thinking most AI integrations today are still essentially fancy search boxes. The AI talks, the human acts. But the real unlock is when the AI can close the loop itself query the database, send the email, update the record without a human in the middle.

The hard part isn't the action itself. It's the non-determinism. How do you build a system where the AI decides when to act, which action to take, and what parameters to pass based purely on context without it going off the rails?

A few things we've learned building this: