Agentic Minimalism: The Human Control Loop
Leverage Loops by Brandon Galang
SubscribeSign in
Agentic Minimalism: The Human Control Loop<br>your agents need a control loop and so do you
Brandon Galang<br>Jun 21, 2026
Share
I have this habit. I’ll be working on something, and a question will cross my mind. Something tangential, something I could probably ignore. Probably something other people would shrug off.<br>Instead of ignoring it, I go down the rabbit hole.<br>AI agents have made this much worse.<br>When your agent can crawl across Slack, GitHub, Linear, Snowflake, Notion, and your local files, those nagging questions that never had answers before are suddenly just a query away. I can fire one off and get a detailed recollection across surfaces: the first time someone mentioned an idea, the first ticket in Linear, the first commit in GitHub, and the first launch update in Slack.<br>It feels incredibly productive. It feels like embracing curiosity and using newfound leverage to investigate more and move faster than I ever could before.<br>Clearly this is the future, right? This is how you get 10x leverage and get ahead?<br>I’ve also been noticing something else: a kind of low-grade exhaustion I can’t pinpoint.<br>I’m not overworked. If anything, I delegate a large portion of what I do. A surprising amount can be done from my phone using voice mode while I go for a walk. I have more capacity than ever to start things and feel less restricted than ever.<br>Yet it all still feels tiring. I end some days drained. Sometimes I have a hard time sleeping and can’t explain why.<br>Agents aren’t doing work for free
When you fire off an agent, you get the reward upfront.<br>You see it thinking and calling tools. You feel progress. Your dopamine starts buzzing as you imagine how long the same query would take manually, crawling through hundreds of thousands of lines of text across several systems.<br>You just did 100x the work for almost no effort.<br>Except it wasn’t free. You signed yourself up for work on the backend.<br>You need to validate the result. You need to imagine where hallucinations or bad assumptions could have entered. When it returns, you have to context-switch back into the thread, leaving attention residue that makes it harder to resume whatever you were doing before.<br>You’re paying a tax you didn’t see at the time of purchase because the purchase felt free.<br>It’s also not just you prompting the agent. The agent is prompting you.<br>Every result surfaces another thread to pull, another question, or a new “interesting” direction to investigate. The tool is generating tremendous amounts of work for you, and you’re absorbing it because it did so much for you.<br>AI reduces the cost of starting work. It does not reduce the cost of deciding what deserves your attention. In many cases, it increases it.<br>This is a control loop problem
When you design an AI agent, you define success criteria, guardrails, and limits on what it should pursue. You give it an objective and explicit non-objectives. You control what tools it can access and what it can change. You cap how long it can iterate before it must commit, stop, or check in.<br>Without those constraints, an agent will chase tangents, clutter its context window, and produce shallow work that misses your point.<br>AI power users naturally learn to do this for their agents. Most never think to build the same guardrails for themselves.<br>I certainly took too long to do it.<br>What I realized is that I need my own control loop: something that keeps me from spreading my attention too thin, limits the number of concurrent threads I allow, and forces me to measure impact rather than activity.<br>Luckily, the principles already exist. Cal Newport has written about them extensively in books like Deep Work and Slow Productivity. In the AI agent era, I think they matter even more.<br>Newport’s principles aren’t productivity hacks. They’re design specifications for the human control loop.<br>Do fewer things: limit concurrent threads
This is work-in-progress limiting.<br>Giving an agent several objectives at once increases the likelihood that it will drift or make mistakes. The same is true for you. Every agent you fire off and every thread you open is a claim on your future attention.<br>An agent “working in the background” is not actually out of mind. Some part of you is tracking that it will return and reserving capacity to evaluate it.<br>The fix is restraint: place a hard cap on how many concurrent threads you allow yourself to have open. This comes from the same logic as a Kanban WIP limit. Limiting work in progress improves flow through the whole system, even when every individual task feels cheap to start.<br>Work at a natural pace: govern iteration
AI creates real acceleration. It also creates the artificial sensation of it.<br>Results that once took hours can return in minutes. Every response surfaces new things to chase. There is no natural pause where you would otherwise decide, “This is enough. I need to move on.”<br>You need an...