Why long-running tasks autonomously carried out by agentic AI aren't the future of doc work, and might just be an illusion

As AI agents become more capable, there's growing eagerness to develop long-running tasks that operate autonomously with minimal human intervention. However, my experience suggests this fully autonomous mode doesn't apply to most documentation work. Most of my doc tasks, when I engage with AI, require constant iterative decision-making, course corrections, and collaborative problem-solving—more like a winding conversation with a thought partner than a straight-line prompt-to-result process. This human-in-the-loop requirement is why AI augments rather than replaces technical writers.