The agent body

People describe agent products by their minds. Ask what any of them is and the answer lists a model, a prompt, a set of tools, maybe some skills, and every product described this way sounds like every other one, because minds are all assembled from the same parts. The real differences between agent products live in their bodies, and the body is the part almost nobody describes.

The boundary problem

An agent that can do anything is weakly defined, and weakness here is a technical property rather than an insult. A definition with no boundary produces no error signal. If the agent is for everything, then no particular outcome counts as failure, no measurement says whether this week’s version beats last week’s, and there is nothing specific to optimize against. This is why bounded definitions improve across versions while unbounded ones stay demos.

The same weakness appears on the human side. A person can only delegate to something they hold a model of, and the model a person holds is mostly a boundary: this is what the thing is for, this is what it will not do, this is where its job ends and mine begins. An agent without a boundary asks its user to hold “anything” in mind, and attention does not bind to anything. It slides off. Plenty of capable agents go unused for exactly this reason. The capabilities are present, but nobody can keep a shapeless capability in mind long enough to build a habit around it.

Both problems are asking for the same missing part: a membrane, a line that says this much is inside and the rest is beyond. The membrane is what turns a pile of capabilities into a thing you can point at, improve, and trust.

Boundaries in biology

Biology settled this question early. A cell is not defined by its contents, which turn over constantly, but by the membrane that holds those contents together and controls what crosses in each direction. Remove the membrane and the cell does not become a bigger, freer cell. It disperses into the medium and dies, because death, in thermodynamic terms, is equilibrium with the surroundings: unlimited free exchange, nothing maintained. Theoretical biology gave this a name, autopoiesis, meaning that a living thing is the process that produces and maintains its own boundary. The free-energy principle in neuroscience makes the matching claim from the other side: a system persists exactly to the degree that it keeps its inside statistically different from its outside.

Bounded things specialize, and specialization is where power comes from. A liver is enormously capable inside its boundary and useless outside it, and the boundary is precisely what makes it improvable, because a defined job produces a defined error. An agent product obeys the same rule. The ones that get better are the ones that maintain a membrane.

The mind and the body

An agent, seen whole, has a mind and a body. The mind is the model plus everything assembled into its context for a single call: the prompt, the tools it is told about, the skills and instructions it is handed, the documents retrieved on its behalf. A model call is stateless. Each time the agent acts, a mind is put together from scratch, and when the call returns, that mind is gone. Whatever continuity the agent has, the model is not supplying it.

The body supplies it, and a body answers five questions:

• How does the agent persist? What state, records, and accounts remain when no model is running?
• What organs does it have? Which functional parts own which piece of its domain?
• How do the organs coordinate? Through what shared state does one part find out what another did?
• What functions do the organs perform together? Which capabilities exist only in the composition, the way circulation exists in no single organ?
• How does the agent maintain unity? What makes its parts present themselves to the world as one continuing thing with one name and one history?

The parts of a body

In practice the answers recur, so a body has a recognizable parts list. There is a durable record of everything that has happened, and the relationship between agent and record runs opposite to intuition: the agent does not have a memory so much as the memory has an agent, one record that successive minds visit, read, and extend. There are organs, functional parts that each own one piece of the domain, one holding money, one holding correspondence, one holding the work queue, and they coordinate through the shared record rather than through each other, which is how an action taken in one part becomes visible to all of them. There are inbound channels, an inbox and webhooks and triggers, through which events reach the body whether or not any model is running; an agent that can only be prompted has half a body at most. There are its own addresses and accounts, the surfaces through which it acts and is known, because standing with other parties attaches to an address rather than to a model.

And there are constraints: spending limits, sending rules, approval gates in front of anything irreversible. The body is defined by these as much as by its capabilities. A wallet with no spending rule is an open channel through which one bad call becomes an unbounded loss, and the rule has to arrive with the wallet, because adding the constraint after the first incident means the first incident was the design process. Constraints are also how the boundary stays a boundary: a limit the body enforces on itself is the membrane doing its job from the inside. Finally, there are written rules the body can be reprogrammed with, which is where human review pays off, since a rule written down today is a part of every mind assembled tomorrow.

Four kinds of agent product

Real agent products sort cleanly under this frame.

A chat assistant has the largest mind and the thinnest body. The mind is a frontier model with conversation context and a few injected memories; the body is a conversation log and a user profile, with no addresses, no accounts, and no organs. The thin boundary explains both of the product’s famous properties. Everyone knows what a chat is for, so the product binds attention instantly, and almost nothing accumulates inside the membrane, so users defect the day a better model ships.

A coding agent has an ordinary mind (a model, a system prompt, file and shell tools) and a superb borrowed body: the repository, with its working tree, branches, tests, and continuous integration. The repository explains why coding agents worked before most other agents did. A repo is a ready-made membrane with a built-in error signal, because a failing test is exactly the bounded, optimizable failure that an unbounded agent never gets to have.

An autonomous business agent inverts the chat assistant. Its mind is swappable and unremarkable, and its body is the heaviest in the list: a payment account, an inbox, a domain, a ledger of records, and the credentials that hold them, with approval gates in front of spending and sending. The boundary is literally the credential set, since inside is whatever the body holds a key to. That is why this class can run unattended, because events arrive through its own channels, and why its progress survives a change of model, because everything accumulated lives on its side of the membrane.

An embedded product agent, the assistant that lives inside an existing application, has a purpose-built mind and no body of its own. It borrows the host’s: the host’s database, permissions, queues, and users. The borrowed boundary explains the whole trade. The agent is good on its first day, because it inherits a mature body, and it can never leave, because the body was never its own and the identity the world sees belongs to the host.

Three questions

Any product in this list, including one you are building, can be checked with three questions:

• Does the agent know what it did last week? A body holds its own history; a visiting mind holds nothing.
• Does an action taken through one surface show up everywhere? Every other place the agent lives should see it, because the organs coordinate through shared state.
• Does it defend its own invariants? Refusing, on its own, the action that would cross one of its limits.

Three yeses is a body. Fewer, and what exists is a mind making visits: capable, stateless, and gone when the call returns.

The minds are converging anyway. Every builder rents them from the same few providers at the same prices, and a better one is available to every competitor on the day it is available to you. The body is the part that cannot be rented, which makes it the part worth designing.