Skip to content
AI: Jobs, Power & Money
22MAR

AI exposure highest among educated women

4 min read
12:34UTC

Anthropic's own usage data reveals the workers most exposed to AI are not who policymakers assume — they are older, female, more educated, and higher-paid.

PoliticsAssessed
Key takeaway

AI's heaviest professional usage falls disproportionately on educated women, inverting the standard displacement narrative.

Anthropic researchers Maxim Massenkoff and Peter McCrory published a study measuring AI's labour market footprint through actual professional Claude usage rather than theoretical capability assessments 1. They introduced "observed exposure" — a metric comparing what AI is actually being used for in workplaces against what it could theoretically perform. The headline numbers: computer programmers face 75% task coverage; computer and maths occupations 35.8%; office and administrative roles 34.3%. The demographic profile of the most-exposed workers overturns the popular image of displacement running downhill to the least skilled. They are "older, female, more educated and higher-paid."

The methodology fills a gap that has weakened earlier research. The most widely cited exposure studies — including the Eloundou et al. GPT-4 assessment published in 2023 — measured what AI could theoretically do if deployed at full capacity. Massenkoff and McCrory measured what is actually happening, using anonymised professional usage data from Claude. The distance between theoretical and observed exposure is where companies, workers, and policymakers need to focus. LLM adoption among US workers rose from 30.1% in December 2024 to 38.3% by December 2025 , but adoption and displacement are different phenomena. Oxford Economics concluded in January 2026 that AI's role in layoffs may be "overstated," finding firms do not appear to be replacing workers with AI at scale . The Anthropic data reframes the question: the issue is less whether displacement is happening than where it is concentrated and who bears it.

No systematic unemployment increase has appeared among heavily exposed occupations since late 2022. That finding sits in tension with the drumbeat of corporate layoff announcements — 45,363 confirmed global tech layoffs in Q1 2026, of which 9,238 cite AI explicitly. But the "suggestive evidence" of slowing hiring among younger workers aligns with the Dallas Fed's data on collapsed job-finding rates for under-25s 2. The pattern across both data sets is consistent: AI is restructuring work at the hiring margin — fewer new positions, changed job descriptions, shifted task allocations — rather than generating mass terminations. Harvard Business Review research by Thomas H. Davenport and Laks Srinivasan found only approximately 2% of organisations reported layoffs tied to actual AI implementation; the remainder cut in anticipation of capability that does not yet exist 3.

The demographic skew carries policy implications that current proposals do not address. Bipartisan AI disclosure requirements and Senator Bernie Sanders' proposed robot tax both implicitly frame displacement as a problem for lower-wage, less-educated workers — the constituency that previous automation waves hit hardest. If AI's actual exposure falls most heavily on workers who already hold degrees and earn above-median wages, retraining programmes built around upskilling the least educated will miss the population bearing the greatest impact. The Anthropic data does not settle the displacement debate, but it does something more useful: it grounds the debate in what AI is actually doing, rather than what it might theoretically do.

Deep Analysis

In plain English

When researchers measure which jobs AI tools are actually being used for — rather than which jobs AI could theoretically do — the answer is counter-intuitive. It is not low-wage manual workers who are most exposed. It is educated, well-paid professionals, and disproportionately women. Think of lawyers reviewing contracts, financial analysts writing reports, or senior administrative co-ordinators. These workers are actively using AI tools — and those tools simultaneously help them work faster and make it easier for employers to need fewer of them. The gap between 'AI can do this' and 'AI is being used for this right now' is smaller than most people assume for this professional cohort.

Deep Analysis
Synthesis

The concentration of AI usage among older, educated, disproportionately female, higher-paid workers means the first cohort facing genuine displacement possesses significant political and economic voice. This inverts the political economy of prior automation waves, which displaced lower-income workers with limited lobbying capacity. Disruption of this demographic could accelerate the policy-response timeline by years relative to prior technological transitions.

Root Causes

High-paying professional roles possess the IT infrastructure and software procurement budgets that enable AI tool adoption; lower-wage roles frequently lack the digital environment for deployment. Separately, knowledge work decomposes into discrete, measurable tasks — the natural unit AI tools operate on — more readily than physical or relational work, structurally biasing observed exposure upward in professional sectors.

Escalation

As AI tools embed in professional workflows, the gap between observed and theoretical exposure will narrow. The Anthropic methodology provides a leading indicator: as professional Claude usage expands into new task categories, those sectors will register rising observed exposure within twelve to eighteen months, ahead of employment data reflecting the shift.

What could happen next?
  • Meaning

    Observed-exposure data provides a twelve-to-eighteen-month leading indicator of employment impact in specific sectors, ahead of official labour statistics.

    Short term · Assessed
  • Risk

    Disproportionate displacement of educated professional women could reverse decades of gender earnings progress faster than existing pay-equity policy frameworks can respond.

    Medium term · Suggested
  • Precedent

    The observed-versus-theoretical exposure methodology may displace expert-survey-based frameworks as the standard for AI impact assessment in policy contexts.

    Medium term · Suggested
  • Consequence

    Continued slowing of junior hiring in high-exposure occupations will compound across cohorts, creating a structural reduction in career entry points that aggregate employment data will not capture until the mid-2030s.

    Long term · Assessed
First Reported In

Update #2 · 45,000 tech layoffs, half may be reversed

Anthropic· 22 Mar 2026
Read original
Different Perspectives
Oxford Economics
Oxford Economics
Concluded AI's role in recent layoffs is 'overstated,' finding companies are not replacing workers with AI at scale. Identified slowing growth, weak demand, and cost pressure as the actual drivers.
Ambrish Shah, Systematix Group
Ambrish Shah, Systematix Group
Warned AI coding tools will erode Indian IT firms' labour-arbitrage growth model by reducing enterprise dependency on large vendor teams.
South Korean government
South Korean government
Enacted the world's second comprehensive AI law, choosing an innovation-first framework over prescriptive employment protections — a deliberate contrast to the EU's regulatory approach.
Corporate executives executing AI-driven cuts
Corporate executives executing AI-driven cuts
Frame workforce reductions as existential necessity. Crypto.com CEO Kris Marszalek and Block CEO Jack Dorsey both described AI adoption as a survival imperative, with equity markets reinforcing the message through immediate share-price gains.
Chinese government (Wang Xiaoping)
Chinese government (Wang Xiaoping)
Positions AI as a job-creation engine to absorb 12.7 million annual graduates and offset 300 million retirements, directly contradicting domestic economist Cai Fang's warning that AI job destruction precedes creation.
Klarna and companies reversing AI cuts
Klarna and companies reversing AI cuts
Klarna's public reversal — rehiring the human agents it replaced with AI after customer satisfaction collapsed — validates Gartner's prediction that half of AI-driven service cuts will be undone by 2027.