Metaintelligence architectureMetaintelligence · Resources · Constraints

Agent economics: autonomy needs a budget

The most reliable limit on behaviour is a resource that runs out, not an instruction in the prompt. When every action and every thought is debited from an account, “don’t do anything unnecessary” stops being a request and becomes a law of the environment.

Metaintelligence architecture · part 6 of 6

The problem of the unbounded agent

An agent without an account is limited only by the patience of whoever pays the provider’s bills. It can go off into a long chain of reasoning, call a tool a hundred times in a row, spawn copies of itself. In a demo this looks like persistence; in operation it turns into uncontrolled spending.

Instructions do not help here. Asking it to “be economical” sets a style but limits nothing. A limit appears when the resource runs out.

Which resources to count

In our environment a participant holds several kinds of resource. There is no single abstract “energy” here; each resource runs out in its own way:

The separation matters because the shortages differ. A participant can be rich in credits and poor in tokens, and then it pays to buy a ready result from a neighbour instead of thinking for itself. Asymmetries like this may give rise to a division of labour that nobody assigned. Whether it really arises, we are testing with experiments, and we do not consider it proven yet.

Thinking as a paid operation

A call to a language model is built into the participant’s cycle as an ordinary operation on its account, not as an external call made somewhere off to the side. The order is as follows:

  1. the participant’s state and goal are serialised into a request;
  2. tokens and, if needed, credits are reserved before the call;
  3. the request goes through an interface not tied to any provider, so the model vendor can be replaced;
  4. actual consumption is debited as incurred, and the unused reservation is returned;
  5. validated changes are applied to the participant’s state, and the requested actions go to a handler.

Why both sides of a trade reserve

When participants exchange resources, the naive scheme of “agree now, settle later” breaks at the first failure: the seller has managed to promise the same thing to two parties, and the buyer has spent credits it no longer has.

So both sides reserve at once. When an order is placed, the seller’s resources and the buyer’s credits go into escrow. From there, simple rules apply:

The main consequence: the same resource cannot be offered twice. That is what separates a working economy from a table of numbers: a promise is backed before anyone has heard it.

What we expect from the economy

  1. Useless activity stops by itself: it does not pay off, and the resource is finite.
  2. A natural priority appears: a participant spends where it expects the greater return.
  3. Exchange arises: depending on the shortage, it is cheaper to buy a result than to produce it, or the other way round.
  4. Costs are visible for each participant and each task, not at the end of the month on the provider’s bill.
  5. Limiting autonomy stops being a question of trust: with a hard ceiling, even a fully autonomous participant will not go beyond its account.

How this carries over to ordinary products

Not every project needs the full economy, but two of its elements pay off almost always:

When a team sees the cost of one solved task, the argument about which model to choose becomes an argument about numbers, and it is much easier to end.

Code and artefacts

The “Metaintelligence architecture” series

  1. Metaintelligence: why the environment around the model sets a system’s ceiling
  2. The agent as a bounded local world
  3. A link as a first-class object: a relationship with state and history
  4. Living graph: topology shaped by work
  5. Consensus without a centre: deciding together without taking anyone’s word for it
  6. Agent economics: autonomy needs a budget

Frequently asked questions

Why an internal currency, when you could simply limit the number of calls?

A call limit does not tell expensive operations from cheap ones and does not let participants trade. An account in resources gives both: a long chain of reasoning costs more than a short one, and a participant with a surplus of one resource can exchange it for one in short supply.

Does this not make the system more complex than it needs to be?

For a single agent, yes; a spending ceiling is enough there. The economy makes sense when there are many participants, the resources are shared and competition for them has to be resolved without manual intervention.

How do you price thinking when provider prices change?

Internal accounting is kept in the system’s own units, and the exchange rate to external prices is set separately. Changing the model vendor then changes the conversion factor, while the logic of the system stays the same.

How we help with this

Read next

Follow the series

If you’re building a similar environment or want to discuss the research with us, write through the form on the homepage.

Email hello@xteam.pro