How I Use AI as an Economist

Notes from using AI in real, months-long research projects. Not a tutorial — what I have learned, what works, and what doesn't. Written for researchers who already use AI and want tricks beyond the basics.

Last updated: Jun 1, 2026. Download PDF version.

Principles

Three ideas that shape how I use AI day to day.

Dispatches

Notes I add as I learn. Sorted by most recently updated. Each card carries a permanent number (#N) and a floating Updated date.

#17 Updated Jun 1, 2026

Git, Dropbox, and AI agents

With agentic tools such as Codex or Claude Code, Git becomes less optional. Not because economists suddenly need to become software engineers, but because agents make many edits, branch off into parallel attempts, and need a clean way to review, merge, or discard their work. The awkward part is that many economics projects still live in Dropbox, the traditional tool for team folders, shared data, and co-author workflows. Dropbox is useful, but it can conflict with Git when both are trying to track the same changing files. Adrien Matray has a wonderful thread on X about exactly this GitHub-and-Dropbox trap for economists. If you are starting to use AI agents for research code, read it before your project folder becomes a sync puzzle.

#16 Updated May 17, 2026

Empirical Work in the Age of AI: three points that stayed with me

Stanford's Empirical Work in the Age of AI is worth watching from beginning to end. The whole event has useful material, but the part I keep returning to is Matthew Gentzkow's comments, starting around 55:56. They gave me three particularly sharp ways to think about research in the age of AI. First, maybe one yardstick for important work is whether the paper could not have been written before AI. Second, management becomes a central skill: researchers used to work almost like self-employed professionals until they were very senior, but AI now gives everyone something closer to a team of agents, and productivity depends on directing that team well. Third, reputation and trust become more important, not less. When the cost of analyzing a dataset and producing an answer falls sharply, the fundamental question is who we trust to produce answers worth believing.

#15 Updated May 16, 2026

AI Brain Drain

I recently read HBR's article on AI "brain fry": the mental fatigue that comes from overseeing more AI agents than our attention can comfortably hold. The part that stayed with me is the productivity warning. More agents are not automatically better if supervising them fragments attention and turns the day into multitasking across outputs. For research, the deeper cost may be even more important: too many parallel agents can crowd out the slow, uninterrupted thinking needed for research design, interpretation, and writing.

#14 Updated May 13, 2026

Digitizing historical records with AI? Read Noah Dasanaike's post.

Fellow econ-history nerds — if you want to use AI to digitize handwritten historical records (censuses, parish registers, tax rolls, ledgers, court books — anything in cursive), save yourself the false starts and go read Noah Dasanaike's writeup. It is the practical, end-to-end account I would have wanted before starting my own pipeline: which models actually read 19th-century handwriting, where the pipeline breaks, how to validate at scale. Better than anything I could add here.

#13 Updated Apr 21, 2026

Git worktrees in Claude Code: keep main clean, run agents in parallel

Research runs for months and most trials fail. Keeping every failed attempt on main pollutes Claude's context; running parallel agents on one tree creates file conflicts. One flag — claude -w <name> — isolates each exploration in its own worktree, so only the winners ever touch main.

#12 Updated Apr 20, 2026

Reviewing Claude Code's work: review the plan, the execution, or both

Principle 3 in practice. Review the plan when re-running is expensive (GPU training, LLM API calls). Review the execution when it is cheap to replicate. The mechanism is the same: pick option 4 on the "Would you like to proceed?" prompt and type /document-review, /codex:adversarial-review, or /ce:review.

#11 Updated Apr 19, 2026

Annoyed by Claude Code permission prompts? Read this.

We want Claude Code to run as an autonomous agent, but it keeps stopping to ask for permission on every bash or MCP call. Two recent features — auto mode and the /fewer-permission-prompts skill — silence the interruptions without resorting to --dangerously-skip-permissions.

#10 Updated Apr 16, 2026

Context management in Claude Code: when to continue, compact, or start fresh

Most usage overruns come from a handful of very long sessions, not many short ones. A practical framework — from personal experience and Anthropic's session management guide — for knowing when to keep going, compact, start fresh, or spin off sub-agents.

#9 Updated Apr 14, 2026

Compound Engineering: a workflow for research projects

Four commands — /ce:brainstorm, /ce:plan, /ce:work, /ce:review — turn a drifting AI session into a structured workflow. How I use them on research projects that span weeks and months.

#8 Updated Apr 13, 2026

The reflection workflow

Turn one hard-won AI session into reusable instructions, skills, memories, or settings so the next similar task starts further ahead.

#7 Updated Apr 12, 2026

Cross-model brainstorming

When one model gets stuck, ask it to package the problem for another model, then bring the second opinion back into the coding session.

#6 Updated Apr 11, 2026

Humanizer: strip AI writing patterns

A small skill for detecting common AI writing tics and rewriting text so it sounds more natural.

#5 Updated Apr 10, 2026

Remote control: approve sessions from your phone

Use Claude Code remote control to keep long tasks moving when you are away from your desk.

#4 Updated Apr 9, 2026

Travel reimbursement as a skill

After a conference, I use a custom Claude Code skill to turn receipts, policies, and templates into a reimbursement package.

#3 Updated Apr 8, 2026

Hooks: automatic context and guardrails

Use hooks to inject context, block dangerous actions, and automate repetitive checks every time Claude Code runs.

#2 Updated Apr 7, 2026

Syncing Claude Code across two machines

A Dropbox-backed setup keeps shared Claude Code context synchronized while machine-specific settings stay local.

#1 Updated Apr 6, 2026

Self-guided learning with AI

Use AI to build a study plan, ask better questions while reading, and keep the exchange candid rather than agreeable.

Resources