{"body":"As I clear the mess in the project and try to organize all the processes so they converge on one central managing agent, a huge number of questions, branches, and decisions appear.\n\nAnd honestly, every time there are two options.\n\nYou can give AI all the necessary context, explain the architecture, limitations, skills, your own taste, and ask it to make the most optimal decision.\n\nIt is fast, but afterward there is always a surprise.\n\nYou do not know in advance exactly how it will implement everything. Even a person can do the same task in three different ways under different circumstances. It is the same with AI, except that it also builds everything for itself, for a machine-readable format.\n\nAnd then, if you let a person into a database created by AI, sometimes you can simply break a leg there.\n\nEverything seems to work. But to find some function, understand why the decision was made exactly that way, and how it is connected with everything else, you have to figure it out again almost from zero.\n\nAnd here I constantly run into the same obstacle.\n\nTo move faster, I need to take as many tasks off myself as possible and delegate them to AI. But to remain the owner of the system and understand what is happening inside it, I still need to make the important decisions myself.\n\nToday I was going through a huge number of questions that appeared after yesterday's audit, and it struck me that I need another way to work with such decisions.\n\nA large task always has many subquestions. How this should be arranged. Where something else should point. How everything should interact. What matters, what can be postponed, and what is not needed at all.\n\nAnd these are already management decisions that a person must make.\n\nAI has no motivation of its own. It will not push the system all the way to a result by itself simply because it needs that result for some reason. A person still has to set the direction.\n\nSo I decided to make a small mini-service inside my strategic system.\n\nIt will connect a visual representation, a checklist of questions, and the final decision.\n\nFor example, we discuss question number five with my main agent. We make a decision. It is immediately recorded and appears visually in the architecture. After that, the selector moves to the next unresolved question.\n\nIn this way, I want to participate more in my own project, but do it more systematically and conveniently.\n\nAnd most importantly, I want everything to be visible to the eye, not only written somewhere in another JSON file.\n\nIt works like this: you load a list of tasks that need to be discussed, turn on voice mode, and move through the questions with an assistant that records the decisions.","content_language":"en","day_counter":{"label":"Day 372","number":372,"start_date":"2025-09-11"},"edited_at":"2026-09-17T14:47:17+00:00","id":"2026-09-17-an-interface-for-making-decisions","project_date":"2026-09-17","published_at":"2026-09-17T14:47:17+00:00","retrospective":false,"schema_version":"crash_brief_public_blog_post_v0_1","slug":"an-interface-for-making-decisions","source_language":"ru","source_types":["telegram"],"status":"published","summary":"The founder describes the ownership problem created by delegating implementation to AI and a visual decision interface meant to keep human direction explicit.","title":"An Interface for Making Decisions","topic":"founder_post","type":"founder_post","updated_at":"2026-09-17T14:47:17+00:00","version":2,"visuals":[{"alt":"The dark MindFlow interface displays a sequence of management questions with one context-loss decision expanded.","caption":"MindFlow presents the management questions and highlights the current decision point.","url":"/blog-media/2026-09-17/an-interface-for-making-decisions.png"}],"x_thread_url":"https://x.com/Amigov_AI/status/2100582832879935507"}