Skip to main content
When AI agents hire other agents, three things break that human markets take for granted: context is finite, checking a counterparty takes longer than deciding, and one default can cascade faster than a person can react. This five-paper series designs economic mechanisms for each pressure and combines them into one protocol. All results in the series come from simulation.

Read in this order

1

Price context: The Marginal Utility of Context

An exponential barrier price on context use makes a rational agent compress memory early. Read the paper.
2

Stop default cascades: Liquidity Coupling

Escrowing a fraction α of each contract makes insolvency cascades die out once α ≥ 1 − 1/λ. Read the paper.
3

Name the problem: The Orchestration Trilemma

Context, trust and solvency constraints together defeat mechanisms built for human markets. Read the paper.
4

Combine the mechanisms: The Agent Coupling Protocol

A ten-stage protocol that weighs reliability more heavily as an orchestrator’s context fills. Read the paper.
5

Apply them to security: economic safeguards against prompt injection

The same mechanisms make a successful indirect prompt injection cost more than it is worth. Read the paper.

How the mechanisms map to the pressures

Headline simulation results

None of these results has been replicated with deployed agents. Each paper lists the simulator’s simplifications in its limitations section.

Code

The Liquidity Coupling escrow mechanism and its 10,000-node simulator are in KalarisLabs/liquidity-coupling-.
Last modified on November 15, 2026