A medieval peasant depended on a lord because the lord controlled the land. Five hundred
years later, we still see a familiar form of dependence: economic power can come from
controlling what others depend upon. If a handful of companies control the AI systems that
businesses increasingly need to compete, our capitalism could develop a relationship that looks
feudal without actually becoming feudal. Policymakers should therefore look beyond AI market
share and ask: can businesses still leave?

If AI becomes infrastructure for production itself, switching between providers could become
increasingly difficult as businesses build their data, workflows, and AI agents around particular
environments to improve efficiency. In this unique time in history, policymakers have an
opportunity to address this before dependence becomes irreversible by monitoring dependency
alongside concentration, preserving interoperability and portability, and scrutinizing exclusive
arrangements involving critical AI infrastructure.

The economist Yanis Varoufakis describes a similar possibility in Technofeudalism: What Killed
Capitalism. He argues that capitalism is being replaced by a system built around “cloud capital”:
algorithms, software, computing infrastructure, data, and digital platforms through which
businesses produce, distribute, and sell (Varoufakis). The important change is that economic
power shifts toward controlling the digital environments through which others operate. The
feudal analogy comes from dependence: those who control an essential resource gain power
over those who depend on it.

But isn't this simply capitalism? In many ways, yes. Capitalism is an economic system based on
private ownership, markets, and profit, while monopoly capitalism occurs when productive
capital becomes concentrated. Concentration alone, however, does not make an economy
feudal. If businesses can freely switch providers or develop alternatives, AI remains productive
capital within capitalism. The difference is not simply that businesses depend on a powerful
company, but that dependence on AI could occur at a fundamental layer of production itself.

AI could push this distinction into sharper focus. If AI-enabled companies can produce the same
output with less labor and expense, firms that fail to adopt AI could weaken competitively. AI
could shift from an optional tool to a requirement for competition. Meanwhile, advanced AI
requires computing, energy, semiconductors, and financial resources at enormous scales. If
those resources remain concentrated, AI capabilities could become concentrated as well.

This creates a potential feedback loop:
more capable AI → greater business dependence → more valuable infrastructure → more
concentration → greater dependence

For AI to create a feudal-like dependence within capitalism, three conditions would need to
emerge: AI must become essential to meaningful competition, AI ownership must remain
concentrated, and businesses must face significant barriers to leaving. A company may
technically have another provider available, but if moving its data, workflows, and AI agents is
prohibitively costly, its ability to switch is only theoretical.

This is where I see a potential middle ground between monopoly capitalism and Varoufakis's full
technofeudalism. I call it pseudo-technofeudalism, or PTF. PTF does not claim that capitalism
disappears. Private property, markets, profit, investment, and capital accumulation can remain.
PTF takes a narrower position: capitalism remains, but AI infrastructure could create a new form
of economic dependence within it.

Evidence suggests this dependence could emerge. Anthropic's Economic Index found that
about 49% of jobs had seen at least a quarter of their tasks performed using Claude (Anthropic).
The World Economic Forum found that 86% of employers expect AI to transform their
businesses by 2030 (World Economic Forum). A 2026 IBM study found that 71% of executives
said switching their primary AI vendor or model would be difficult (IBM Institute for Business
Value). Together, these findings suggest that AI is becoming more important to production while
businesses are already beginning to face switching barriers.

For PTF, the important question is not simply whether AI eliminates jobs. It is whether
businesses become dependent on AI to remain competitive. The internet offers a useful
precedent: while it became infrastructure for information and communication, AI could become
infrastructure for production itself. If businesses build their workflows around particular AI
ecosystems, leaving them could become increasingly costly.

A monopoly may control a market; PTF requires control over a fundamental layer of production
itself. This is why policymakers should look beyond market share.

First, regulators should monitor dependency alongside concentration, asking how difficult it
would be for businesses to leave. The OECD should monitor Big Tech’s contracts, data-egress
fees, limited interoperability, and proprietary ecosystems as potential switching barriers
(Organisation for Economic Co-operation and Development).

Second, policymakers should preserve portability and interoperability where technically feasible,
so businesses can move data and systems between providers without barriers like time or fees
becoming a threat to competition.

Third, competition authorities should scrutinize exclusive contracts and vertical integration
involving critical AI infrastructure. The Federal Trade Commission has already examined major
AI-cloud partnerships over concerns involving computing access, switching costs, and
exclusivity, and they should continue to do so by investigating mergers (Federal Trade
Commission).

None of this means concentration itself is necessarily harmful. AI requires enormous amounts of
capital and infrastructure, and integration can produce genuine efficiencies. The goal should
therefore not be to prevent successful AI companies from becoming large, but to prevent
concentration from becoming irreversible dependence.

The most important question surrounding AI power may not be who has the largest model or
market share. It may be whether businesses can still leave. That is the point at which AI
concentration stops being merely a question of who sells the technology and becomes a
question of who controls the economy.