When I Narrowed My Human Inputs Down to Just Todoist and Discord, the System Started Running Itself
Originally published on my Substack . I'm a Microsoft MVP based in Japan, writing in English about the AI agent systems I actually run in production. AI tools have multiplied. So have agents, skills, and automation scripts. And yet, somehow, my hands are never free. I wake up, open a dashboard, check notifications, go look at the logs for a failed job, and think, "wait, where was that process…
The author of this article, a Microsoft MVP from Japan, describes how they narrowed their human inputs down to just two: Todoist for task management and Discord for conversation. This simplification was intended to reduce the number of places a human needs to check for information, as each additional automation added another entry point to monitor.
The author explains that each new service or automation they added resulted in more UIs, config files, and logs, making it harder to keep track of everything. They outline three reasons why reducing entry points is more difficult than reducing features: entry points multiply unnoticed, the "last ten percent" of automation still requires human monitoring, and entry points are only reduced by making a conscious decision not to add new ones.
The author references their "Ebi Workspace" system, which uses AI to manage tasks and conversations, but acknowledges that this design requires further development to better handle invisible information that becomes inaccessible when entry points are closed. They plan to report on the actual results of implementing this two-entry-point system, including the number of automated processes, their execution frequency, failure rates, and the challenges faced in maintaining this design.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
