On Bio Tokens and Agentic Thinking
Since publishing my last essay on agentic operating, the conversations it sparked have pulled me toward a deeper layer of the idea.
What I found myself trying to explain was how these systems change what I can give my attention to. There are only so many things I can think about carefully, people I can be fully present with, and decisions I can take responsibility for in a day.
Lately I have been calling these bio tokens. Not API tokens. Human ones. Units of attention, judgment, synthesis, emotional steadiness, and cognitive energy. Each of us gets a finite daily budget. The budget changes with sleep, stress, and mental state. Some days the cap is high. Some days it collapses. But there is always a cap.
That cap matters more than most productivity systems admit.
A lot of ambitious people still behave as if the problem is scheduling. Better calendars. Better task managers. Better routines. Those things help, but they miss the deeper constraint. The real bottleneck is how many high-quality bio tokens you can deploy before your thinking degrades. Once those are gone, the day may continue, but the sharpness does not.
This is why two hours of clear thinking can outperform ten hours of fragmented motion. And it is why the most valuable systems are not the ones that help you do more things. They are the ones that help you spend your bio tokens on the right layer of the stack.
That is increasingly how I think about leverage.
What Attention Makes Possible
There is a limit to the token metaphor. It can make attention sound like something interchangeable, as though an hour spent listening to a friend and an hour spent sorting documents were simply two withdrawals from the same account. What matters is also what happens to us while we spend it.
How we spend our attention also shapes the attention we can bring to the next thing. We develop judgment by making decisions and living with their consequences. We discover what we think by trying to explain it. We learn to understand another person by giving them enough room to surprise us.
That makes bio tokens an unusual resource: spending them can develop our capacity. Some demanding work does more than produce an immediate result; it can strengthen our ability to notice patterns, understand complex situations, make sound judgments, and act effectively. A philosophy of leverage therefore needs to account not only for the effort a tool saves, but also for the skills, judgment, and resilience that effort can build.
This complicates the ambition to save bio tokens. Some of the effort I would like to remove is also how I learn. An agent can assemble a convincing argument before I have understood the problem well enough to challenge it. The work may look finished while my understanding remains unfinished.
So I need to be careful about what I delegate. Reconstructing where I left a document rarely changes me. Working through why I disagree with it might. The distinction depends on what I am trying to learn and what responsibility I will carry afterward.
The architecture I want should help me stay with worthwhile difficulty. It should give me more room to follow a question, develop my judgment, or pay attention to someone whose answer I cannot anticipate. Those are things I want to spend my life on.
Engineering Saw It First
Zed's framing around agentic engineering put language around something real: quality responsibility stays with the human, taste and craftsmanship matter, and directing agents is its own craft. Engineering's culture of tools, automation, and explicit feedback loops gave this approach somewhere to develop.
Any field where the product is judgment is governed by the same constraint. Investing. Research. Operating. Writing. Strategy. In each case, the visible output may differ, but the hidden bottleneck is the same: a finite human capacity to absorb context, hold state, compare possibilities, and make good calls.
That is the real abstraction. Agentic engineering is not the full category. It is the first clear instance of a broader shift toward agentic thinking.
The New Problem Is Not Work. It Is Token Allocation.
Once you see knowledge work through this lens, a lot of bad productivity advice starts to look shallow.
The question is not: how do I get through my inbox faster?
The question is: what am I spending irreplaceable bio tokens on that should have been converted into cheaper digital tokens?
That distinction matters.
A bio token is scarce, variable, and tightly coupled to human judgment. A digital token is cheap by comparison. It can be used for retrieval, assembly, formatting, summarization, cross-referencing, drafting, and state tracking. Digital tokens are imperfect, of course. They need constraints. They need supervision. They need taste upstream and judgment downstream. But they are abundant enough to absorb a growing share of lower-order cognitive work.
From my own experience, most leverage has come from learning how to make that conversion deliberately.
At first, the gains are small: offload note cleanup, task extraction, first-pass research, context assembly before a meeting or a writing session. Then, over time, the system becomes more ambitious. It starts carrying more of the surrounding state: what changed, what is unresolved, what evidence supports a claim, what counterarguments matter, what should be followed up tomorrow.
The point is not that I stop spending bio tokens.
The point is that I stop spending premium bio tokens on retrieval, coordination, and re-entry. I can spend them on higher-order thinking instead: framing the real question, pressure-testing the thesis, noticing what does not fit, making the call.
This is what agentic systems are really buying you when they work well. Not raw speed. Better allocation.
Delegation Is Old. Loop Closure Is New.
None of this begins with AI.
Long before models, ambitious people learned how to extend themselves by delegation. Founders hired chiefs of staff. Executives built layers of assistants and operators. Investors built research teams. Institutions created entire managerial systems to preserve executive attention for the decisions that mattered most.
Empires were built this way.
In other words, the basic insight is not new: if human judgment is scarce, protect it.
What is new is the speed at which loops can close.
Traditional delegation creates leverage, but it also creates coordination overhead. Every handoff needs framing. Every follow-up needs clarification. Every update carries latency. Every loop depends on human availability. The work moves, but the metadata around the work moves more slowly.
That metadata is where much of the hidden drag lives.
Why does this task matter? What changed since yesterday? Which source is strongest? What remains uncertain? What is blocked? What is the next best question? What prior context should shape the decision?
In older systems, that metadata was expensive to keep current. It lived in scattered documents, in assistants' heads, in status meetings, in memory, in half-written notes. A lot of executive energy was burned just reconstituting the state of the work.
Agentic systems change this because they can carry the metadata forward continuously.
They do not just help complete a task. They help preserve and update the context around the task. They can ingest the new information, compare it against prior state, mark what changed, suggest what matters, and tee up the next loop. That means the bottleneck is no longer just execution speed. It is the combined speed of execution and context propagation.
That is where the day-to-day velocity becomes visceral.
You do not just feel that more work is getting done. You feel that the system around the work is moving with you. Context is fresher. Open loops close faster. Re-entry costs fall. The distance between thought, test, feedback, and revision shrinks.
This is not a small optimization. It changes the texture of operating.
What This Looks Like In Practice
I built a system for myself around this idea.
The core goal was simple: spend fewer bio tokens on remembering, reassembling, and restarting.
It has three loops.
First, stream capture: one place to drop thoughts, notes, tasks, observations, fragments, whatever passes through the day. No ceremony. Minimal friction.
Second, daily closeout: an agent-assisted triage process that turns the stream into structured next states. Tasks become tasks. ideas become research threads. observations get linked to ongoing work. What matters gets surfaced in the context of my priorities.
Third, morning briefing: a prepared context layer for the next day. Open loops, calendar, project deltas, research movement, outstanding questions.
The system matters less than the principle behind it.
I am not trying to automate myself out of the loop. I am trying to preserve my best bio tokens for the part of the loop only I can do.
You feel this most clearly when I start exploring a new domain. The loop now closes differently. I can capture a question in passing, have the surrounding research and counterarguments assembled into a working frame, review it the next morning with context intact, push on the weak points, share it with others, and update the thesis quickly. The gain is not only that I reached fluency faster. It is that far fewer bio tokens were burned on reconstruction.
The same daily budget now gets spent on sharper questions.
That is the unlock I keep feeling.
Toward an Architecture of Leverage
This is why I think the implications extend well beyond engineering.
The frontier is not merely better chat interfaces or smarter copilots. It is the design of systems that convert low-value bio-token spend into digital-token throughput while preserving human responsibility for quality.
That last part matters. This is not a case for surrendering judgment. If anything, the better the system gets, the more valuable human taste becomes. Someone still has to define what matters, detect when the model is wrong, choose between trade-offs, and decide when a conclusion is actually good enough to act on.
But the composition of the day changes.
Less time spent rebuilding context. Less energy spent on first-order assembly. More capacity for second-order reasoning. More room for taste. More room for synthesis. More room for actual thought.
That is why I think the people who benefit most from agentic systems will not simply be the ones who “use AI.” It will be the ones who understand cognition as a scarce resource and design around it accordingly.
That leaves a question the system cannot settle for me: what deserves the attention it gives back? I can use it to take on more work, understand a difficult idea, or be more present with another person. I can also fill it with commitments I have never properly examined. Greater capacity makes that choice more consequential.
An architecture of leverage should preserve room for the effort through which I develop my own judgment. It should help me carry my responsibilities while becoming more capable of choosing them.
How I spend my bio tokens shapes both what I contribute and who I become. That is the choice I want these systems to give me more room to make.