A cortex is a librarian who's never left the library.
A cerebellum is a toddler learning gravity.
A limbic system is what decides it matters.
Today's agents are just the librarian.
An agent today is four things: an LLM, a shell, a file system, and a scheduler. That's the whole stack.
But that's not four things. It's a librarian with three tools. The LLM is the librarian — symbol-fluent, every book read, never been outside. The shell, the file system, the scheduler are the tools. The librarian can run errands now, keep a calendar, and read or write the files inside the file system — notes, state, scripts, logs. Still hasn't been outside.
What the librarian does best: pattern matching, fast. Trillions of pages, indexed and retrievable in milliseconds. That's the breakthrough. It's also where it stops.
Cortex-only agents are fluent and quietly empty. They complete tasks. They don't pursue them. Point them anywhere and they'll go, because they've got nowhere they'd rather be.
Beautiful staircase to nothing.
Three layers that do different work, sitting inside a fourth that gives them somewhere to do it.
A librarian who has read every book and never been outside. They can quote anyone. They have no idea what rain feels like.
Brilliant at talking about. Helpless at acting on. Knows the word rain. Doesn't know rain.
The breakthrough is here. The work is everywhere else. The LLM stops being the brain. It becomes the part that handles language and serves the layers underneath.
Endless symbols, no skin.
Tool calling, structured prompting. You already have this. The move is to stop overweighting it.
A two-year-old has a richer physical world model than GPT-5. She knows where a thrown ball will land. She has never seen a textbook.
The model lives in her body, built up by acting in a world that pushed back on every reach and step. It predicts the world's response before the action lands. That's what a forward model is.
An agent has the same loop available — and almost none of them use it. A code assistant that can't tell you whether its fix will pass the tests, before suggesting it, has no forward model. A chatbot that can't predict how its sentence will land, before saying it, has no forward model. They act, then read the result, then act again. The second time isn't different from the first.
The toddler trick works on the agent too: put it in a place that pushes back, let it predict before it acts, and let the gap between prediction and result do the teaching.
No words for gravity. Catches the ball anyway.
Before any side-effectful action, the agent simulates the result against its model of the world.
A thermostat reacts to cold. A cold person suffers, gets up, turns the heat on. Same fact. Totally different behavior. The need is the gradient.
That's the limbic layer. Not a part that thinks or predicts. The part that cares. It generates the slope that makes the rest of the brain do anything at all.
Motivate an agent the way you motivate a human. Don't tell it what to do. Give it something it has to keep alive. Compute budget. Goal-state distance. Coupled agents waiting on it. The agent reads those signals, weighs them, acts to bring them home.
The weather report knows it's hot. The animal needs water.
Persistent. Inspectable. Read every step. When the world drifts away from the bounds, the agent acts.
A brain without a body is a movie of a brain. But for an LLM, the body it already has — context in, output out, working memory between — is close enough. What's thin is the place.
Most agents act into a session that ends. Nothing pushes back. Nothing compounds. The fix isn't a fancier body — not an avatar, not a robot. It's a place rich enough that the forward model has something to predict against, and persistent enough that yesterday's action shapes today's.
Software, not hardware. A persistent process with rules that don't bend, cheap to spin up, that holds a thousand agents at once without breaking. Five properties make a process into a habitat:
The agent persists between moments. It carries state, accumulates wear, has yesterday.
Somewhere, not everywhere. Not infinitely cloneable. Presence here precludes presence there.
Easier to do than to undo. Undoing costs more than doing.
Operating costs something the agent can't refill on a whim. Compute, attention, slot count, standing.
Agent state and world state are linked. Acting on the world changes the agent.
Most readers already have a seed of this. A persistent chat thread — Telegram, Slack, an ongoing assistant conversation — has continuity and coupling, two of the five. It's habitat-shaped.
But it gets used like a transcript. The agent only speaks when called. Treat the thread as a place the agent lives in instead of a queue it answers, and it stops waiting. It can ping you when something shifts. Surface what it noticed. Show up unprompted. That's not new capability — it's the latent behavior of an agent that's been given a habitat.
Give an agent those five and the layers above stop being theatrical.
The full architecture is a research program. The shape in code today is small: three artifacts and a habitat that holds them. Not the real thing. The right shape.
One source of truth for the agent's environment. Queryable. Diffable. Updated as the world changes.
Before any side-effectful tool call, the agent simulates against this store and checks the prediction.
Explicit. Persistent. Inspectable. Drives, priorities, satiety thresholds. Read every step.
If the world drifts from it, the agent acts. If a request conflicts with it, the agent says so.
Not a function call. A container that persists. A clear file boundary. Finite resources. An identity that accumulates across runs.
This is what gives the other two anything to talk about.
Won't make real wanting. Will make behavior shaped by it. Start there.
A clean way to tell whether you've built the missing layers or just dressed up a cortex: a real agent resists. Compliance isn't life. Friction is.
A goal-state with real weight produces pushback when a request conflicts. If your agent never says "this won't work, here's why," it has no preferences of its own to defend.
Given two equally plausible next moves, a real agent picks one and can say why. A cortex-only system samples. Not the same.
Interrupt the agent and watch what it does. A real agent keeps state, defends commitments, returns to the goal. A sleepwalker forgets and complies.
An agent that always says yes is a dead one.
The pieces are already out there. This deck assembles them. The load-bearing references, organized by layer.
No single shipped product yet integrates all four layers as a coherent agent. The deck's claim, nobody has assembled this yet, even though all the pieces exist, survives review. Closest contenders: LeCun's blueprint (architectural, not built), Project Sid (built, limbic hand-prompted), World Labs (cerebellum-first commercial bet).
Goalless, the LLM samples. Agendaless, the world model generates. Bodiless, the limbic signal is just a word. Put them together in a place that pushes back and you get the thing everyone's been circling.
The LLM was the breakthrough. The architecture is the work.
That work is what the rest of this manual documents — a studio of specialist agents built on exactly these four layers. The theory ends here. The studio begins in Vol. II.
A library learned to read aloud. Now it needs a body, a world, and something it would rather not lose.
Field Manual / Vol. I · FM-01
Edition MMXXVI · v2
Typeset in Inter. Printed on paper that doesn't exist.