Extending The Horizon Of Agent Autonomy Is A Testing Problem

I’ve talked before about how improbable long-horizon autonomous agentic workflows are. Every step is a throw of a weighted dice, and with each additional step the probability of success goes down. On top of this, decisions have dependencies, and this means that errors can compound downstream. Take a wrong turn at step N, and step N+1, N+2, N+3 could well build on that mistake. The other side of the equation is verification. Mistakes aren’t a problem if they’re caught before they compound. So we now have two components: the probability of an error, and the probable number of subsequent steps before the error’s detected. More bluntly, if the agent f***ed up, how soon would we/it know? The E in my CRESS principles for context engineering stands for “Empirical” – input contexts should be grounded in observed reality, not unverified model output. I visualise raw model output as being like untreated sewage. Yes, there’s water in it. But it’s not safe for the model to drink. To make it safe,…