AI Agents for Economic Research — Korinek guide

At a glance

Type

Tutorial / template

Workflow level

Workflow unspecified / not applicable

Organisation

Anton Korinek

Year

2025

Disciplines

Business & managementEconomics

Tasks

Data analysisLiterature researchResearch codingWorkflow orchestration

Entry updated

2026-10-16

Evidence & verification

Source level

Institutional report
Grounded in a report published by the institution that produced the system, without peer review.

Outcome verification

Not empirically evaluated here
A documented resource or intended workflow, not a demonstrated academic outcome. No empirical benefit is established by its inclusion.

Sources checked

2026-10-15 (UTC)

Primary-source feature/workflow review only. Performance, uptake and promotional claims are not treated as validated research gains.

Source-checked does not mean independently reproduced. See the Method page for how these labels are assigned.

Sources (1)

Research applicability

Anton Korinek’s August 2025 guide introduces AI agents for economic research with worked instructions for literature reviews, econometric code and data analysis.

Getting started

Read the reader’s guide, choose one bounded example, inspect tool permissions and reproduce its outputs before extending it.

Maintenance

Current operational availability and maintenance were not tested; this recommendation rests on the dated source snapshot.

License

Licensing, service terms and rights to input data must be checked before adoption; no independent license audit performed.

Workflow & human oversight

Resource-level classification is intentionally unspecified; instantiated workflows may differ. Humans define objectives, control data access, and check outputs.

Workflow level is not an evidence score; higher is not better evidence.

Approach

The guide explains agent planning and tool use and supplies step-by-step examples for building research assistants.

Limitations

The reviewed item is the 2025 update, not proof that the new material itself received the original JEL article’s peer review. Claims about rapid implementation are author claims; examples were not run and model APIs may change.

Reproducibility

Reviewed a stored primary-source extract accessed 2026-10-15. No software, model or claimed outcome was independently reproduced.

Adoption requirements

Access to the guide, suitable model/tool services and an economist able to validate code, data and inference.

Comments

No comments yet.

Add a comment

Comments are held for moderation before appearing. Critical or corrective comments are welcome — especially evidence that an entry overstates what has been verified.