How will documents evolve when AI agents become ubiquitous? In a world of AI agents, does the repository become the source of truth—where humans declare intent, agents turn it into executable artifacts, and documents represent a targeted view of something more powerful?
Repositories aren’t where code lives anymore—they’re where **knowledge is manufactured**.
And increasingly, it’s not humans doing the work—it’s agents, with humans supervising the factory.
Neural networks are more useful when placed in a suitable, specialized environment.
AI software demands new approaches to testing that go far beyond existing software testing methodologies. And with the rapid evolution of AI model capabilities, the need for the software engineering community to innovate new approaches to AI software testing is urgent.
Prompts are our way of communicating intent to AI foundation models and large language models. The PL and SE communities have great experience understanding how to build robust software that should now be applied to AI model prompts.
