Behind the Craft · Sunday, June 28, 2026
Jess Yan from Anthropic explains the evolution of AI agents from simple prompt-response loops to autonomous, self-discovering actors capable of long-running tasks. These agents can now interact with third-party systems and sensitive data, requiring enhanced permissioning and observability.
“We've really evolved from agents being prompting loop to agents being autonomous, self-discovering.”
“And long running actors, we set them tasks overnight and then we wake up and backlogging results and bugger our squashed.”
“And that that level of access now requires permissioning, uh, observability, uh, steering, not not in the same way that it was just questions and answers before.”