Research

AI at Your Side: The Student's Guide to Smarter Learning

with Sebastian Galiani. Oxford University Press, 2026.

AI at Your Side is a practical guide for college students who want to use artificial intelligence to learn more, not to cut corners. Instead of a quick list of apps and tricks, it teaches a lasting way of working with AI across the subjects students actually study, from writing and research to mathematics, coding, data, economics, and finance. Its message is steady throughout: AI should sharpen your thinking, not stand in for it. Written by a senior economist and a student of the first AI-native generation, the book turns every assignment into a chance to understand more and depend less.

Measuring Efficiency and Equity Framing in Economics Research: LLM-Based Evidence from 1950 to 2021

with Sebastian Galiani, Ramiro H. Gálvez, and Franco Mettola La Giglia. Revise and Resubmit, The Economic Journal (Special Issue on AI Measurement in Applied Economics).

We measure how frontier research frames what is normatively at stake along the efficiency and equity dimension. We develop and validate an LLM-based measurement pipeline and apply it to 27,464 full-text journal articles from 1950 to 2021. Efficiency-focused framing rises through the late 1980s, then declines as equity-related framing expands after 1990, especially in applied work and policy evaluations. By 2021, papers with an equity component are about as common as papers framed purely around efficiency. President transmittal letters in the Economic Report of the President show a similar post-1990 shift toward equity, providing an external benchmark.

PDF

Deep Research on a Loop: Using AI Agents to Construct Economic Datasets

with Santiago Afonso, Sebastian Galiani, and Ramiro H. Gálvez.

Constructing datasets from primary sources is one of the costliest tasks in empirical economics. We propose Deep Research on a Loop (DRIL), a methodology that uses AI agents to assemble datasets from publicly available sources. DRIL applies a fixed research instrument across a mapped unit space (e.g., countries by years), with a two-stage architecture separating design from implementation. The instrument specifies variables and coding rules, an evidence policy governs sources and citations, and data quality mechanisms track gaps and uncertainty explicitly. We exercise DRIL on a 2025 update of the Global Tax Expenditures Database for eight Latin American and Caribbean countries. The run produces 129 sources and 136 evidence records, covering 22 qualitative fields fully and 6 quantitative estimate types with documented gaps, at the cost of a standard LLM subscription comparable to a few hours of research-assistant work. We argue that even partial automation of dataset construction can shift the production function of empirical economics.

PDF

Chatbots, Agents, and the Choice of Econometric Software

with Sebastian Galiani and Federico A. López.

We study how large language models write code for econometric analysis. We measure how performance varies with the statistical software (Stata, R, or Python), the prompt, and the degree of agency, with three levels from a chatbot that only writes code to a more agentic harness that executes its own code. We create a benchmark of applied econometric and statistics tasks. We find that a higher degree of agency afforded to the model through the harness produces higher success rates, at a higher cost. We also analyze this trade-off between gains in correct output from more agency and token costs. The main results use Claude Code. We reproduce the results using OpenAI's Codex and DeepSeek-V4 through OpenCode.

PDF

Divergence in Climate Change Communication: LLM-Based Evidence from the IPCC and the Press

with Sebastian Galiani and Franco Mettola La Giglia.

Public summaries of IPCC climate assessments lean toward the more severe end of the technical evidence. The pattern appears at two stages: the IPCC's lead authors and member governments produce the Summary for Policymakers (SPM) from the Technical Summary (TS), and newspapers then cover the SPM. We use LLMs to score about 114,000 matched claim pairs from all six Assessment Reports (1990 to 2023) and ten major US and UK outlets. Both stages systematically shift toward the more severe end of the source while staying inside the IPCC's accepted scientific ranges. The shift comes mainly from emphasizing higher-impact magnitudes within reported ranges, less from uncertainty compression, and almost none from selecting worst-case emissions scenarios. Left- and right-leaning outlets show similar patterns.

PDF

The Empathy Channel in Fertility

with Sebastian Galiani. Submitted.

Being around babies makes people want babies. We formalize this observation as the empathy channel: exposure to infants in the social environment activates neurobiological mechanisms that increase the desire for parenthood. As fertility declines and children become scarcer, this affective stimulus weakens, further eroding the motivation to have children. We embed the mechanism in a two-group overlapping-generations quantity-quality model that admits closed-form solutions and nests the standard framework as a special case. The empathy channel generates a positive externality, since each birth raises others' desire for children, making the decentralized equilibrium inefficient. We characterize the optimal per-child subsidy and show that the first-order Pigouvian rate overshoots the general-equilibrium optimum by 23–32%. The optimal targeting rule follows a Ramsey-like logic, so the subsidy should be directed at the group generating the most externality per fiscal dollar, which need not be the group with the largest externality per child. The calibrated model suggests that the empathy channel can account for 3–33% of the fertility decline, with 13.4% at the baseline. At this baseline, the optimal subsidy raises welfare by 0.22% in consumption-equivalent terms.

PDF

Composition Beats Collapse: Insights from the Bisin–Verdier Model on Endogenous Fertility Reversal

with Sebastian Galiani. Submitted.

Fertility rates have fallen below replacement in most countries, fueling predictions of demographic collapse. We show these forecasts overlook a crucial fact: societies are not homogeneous. Using the Bisin–Verdier model of cultural transmission with endogenous fertility and direct socialization, calibrated to U.S. and global data, we find that high-fertility, high-retention groups persist, gain share, and lead the total population to grow. Even if fertility remains below replacement in every country, extinction is unlikely. Simulations imply continued growth with pronounced compositional change, driven especially by religious communities with high fertility. In our ten-generation world calibration, Muslims become the largest tradition.

PDF

Easy Like Sunday Morning: Organizational Design and Physician Agency in Birth Timing

with Jimena S. Ferraro and Franco M. Vazquez. Submitted.

Cesarean rates differ sharply between private and public hospitals in Buenos Aires, even though payments do not vary with delivery mode in either sector. We argue this gap reflects organizational design rather than procedure prices. In the Buenos Aires metropolitan area, individualized private and team-based public maternity care coexist within the same labor market. Using ex ante preferences and medical records for low-risk first-time mothers, we document a preference margin and a timing margin. Stated preferences for cesarean predict scheduled procedures strongly in private hospitals and not at all in public ones. Elective cesareans in private hospitals cluster on boundary working days (the Monday or Friday adjacent to a weekend or holiday), and the intrapartum cesarean rate is about 13 percentage points higher on working than nonworking days in private hospitals, but indistinguishable from zero in public ones, a gradient that reflects selection induced by the timing margin. A simple model rationalizes both margins through the opportunity cost of physician time, internalized only when physicians are residual claimants of their own schedule. Organizational design, not procedure prices, is the primary lever behind the discretionary component of cesarean use.

PDF

Minimum Slaughter Weight Regulation in Cattle Markets: Evidence from Argentina

with Federico Sturzenegger and Franco M. Vazquez. Submitted. M.A. thesis.

A minimum slaughter weight forbids slaughtering animals below a legal threshold, a rule meant to raise meat production. We evaluate it in a Faustmann competitive equilibrium with endogenous breeding, a binding land constraint, and two technologies, calibrated to Argentina. With a single technology, discounting makes producers slaughter below the supply-maximizing weight, so a moderate floor raises supply. The supply gain is small, and once the transition through the cattle cycle is priced, the floor delivers no welfare gain. With pasture and feedlot sharing the market, equilibrium slaughter weights are 408 and 346 kg. A uniform 420–450 kg floor can cut welfare by 13.2–18.8% of revenue in present value where cattle is the dominant land use, because feedlot output losses dominate pasture gains. Argentina's floor did not bind the representative producer, so the 2026 repeal carried effectively zero welfare cost and a tighter one would have been harmful. As middle-income agriculture turns dual, a capital-intensive segment beside a land-intensive one, a uniform instrument written for a single technology misfires once that structure takes hold.

PDF