AI Workflow

28 articles

A Starter Kit for the Economist’s First Week in Claude Code

A small set of copyable files that gives our second Claude Code session everything the first one forgot: seven files, installed in about ten minutes.

Jul 2026 · Methodology

How to tell whether a double machine learning estimate is right

Double machine learning in Python: why a naive plug-in reads a true effect of 1.0 as 0.55, how cross-fitting recovers 0.97, and the confounder it still cannot detect.

Jul 2026 · Methodology

How do we know an AI's estimator does what we meant?

AI-generated econometric code can run without error and still be wrong. A routine to verify it: spec the low-visibility choices, plant a known truth, and read the code against its source.

Jun 2026 · Methodology

When a policy reaches only a few units: rolling difference-in-differences (lwdid)

Rolling difference-in-differences (lwdid) gives credible effects from one treated unit and a few controls, and with so few units the transformation choice drives the answer.

Jun 2026 · Methodology

Logistic regression beats LLM readouts on survey prediction

On a real survey prediction task, a plain logistic regression beat a language-model activation pipeline, AUC 0.769 vs 0.747; steering changed nothing useful.

Jun 2026 · Methodology

Prediction-powered inference corrects AI survey imputation

Treating AI-imputed survey responses as data understated prevalence threefold; a regression adjustment lets predictions sharpen estimates without harm.

Jun 2026 · Methodology

Steering vectors estimate an average regression gradient

Activation steering approximates an average regression gradient, cosine 0.63 in our data, and classic estimator choices change how hard the vector steers.

Jun 2026 · Methodology

Running Claude Code skills, for applied economists

A setup guide for the TETS Claude Code skills introduced in the tool series (papers-md-generator, replication-package-analytics, attribution-audit-network).

May 2026 · Methodology

A field map for causal-inference methods

A Claude Code skill that builds a navigable citation network around a single method family, surfacing the seminal references, the current authors, the recent…

May 2026 · Methodology

A reference library for empirical methods

A Claude Code skill that turns a DOI or PDF into a structured papers.md block documenting the estimator, identification strategy, and named assumptions, with…

May 2026 · Methodology

A common shape for econ replication packages

A Claude Code skill that crawls econ replication packages and produces a panel dataset of 12 structural-compliance metrics per package.

May 2026 · Methodology

Well-Executed But Not Important: Reading the Record

When AI thins out the technical-flaws desk-rejection pretext, editors will have to learn to say 'well-executed but not important' on the record.

May 2026 · Methodology

Cycling Through Bad Ideas Faster: A Worked Example

How AI-augmented iterative critique compresses the cost of discarding bad ideas in applied research, illustrated through three coding rules, a controls…

May 2026 · Methodology

A Pre-Analysis Plan for Your Coding Agent

A three-layer architecture, rule, gate, and verification, for keeping an AI coding agent disciplined, and why trained priors beat a system prompt.

May 2026 · Methodology

Connecting Claude to FRED, Census, and More

How to connect Claude Code to external data sources like FRED, Census, and Google Scholar, bringing integrated research workflows into natural conversation.

Mar 2026 · Methodology

Hooks: Automation Without Asking

Hooks are automatic triggers that run without asking - like auto-save, but for research tasks. A power-user feature, entirely optional.

Mar 2026 · Methodology

Reading Our Analysis Files: How Claude Sees Our Research Code

How Claude Code explores research projects using three core tools: Read (look at a file), Glob (find files by pattern), and Grep (search inside files).

Feb 2026 · Methodology

Why It Forgot Everything: Understanding Context

Understanding how AI context windows work, why sessions reset, and how to work with this fundamental limitation of large language models.

Feb 2026 · Methodology

What Claude Code /insights Reveals at Every Stage

How to read a Claude Code /insights report at beginner and intermediate levels: the same usage data yields different lessons at each stage.

Feb 2026 · Methodology

Your First Session: What Claude Code Is and Isn't

A practical walkthrough of what Claude Code can and cannot do, with prompting patterns and a complete first-task example.

Feb 2026 · Methodology

Research Phases Need Different Prompts

Exploration, implementation, and documentation require different AI prompting strategies. Match the prompt to the phase.

Jan 2026 · Methodology

The Verification Tax: Every AI Output Needs Checking

Every AI output needs checking. Building verification into the research workflow to catch fabricated citations and errors before they compound.

Jan 2026 · Methodology

Context Window Budgeting: Treating Tokens as a Finite Resource

Treating an AI context window as a finite budget: when to spawn sub-agents, when to work directly, and how to keep a long session from degrading.

Jan 2026 · Methodology

End-of-Session Hygiene: What to Capture Before Context Resets

What to capture before an AI context window resets, and how five minutes of end-of-session notes saves twenty minutes rebuilding context tomorrow.

Jan 2026 · Methodology

Creating Skills for Research

Skills are recipe cards for research tasks. Write the steps once, save them in a file, and Claude Code follows those instructions whenever needed.

Dec 2025 · Methodology

Building Our Research System: Putting It All Together

How CLAUDE.md, skills, hooks, and MCP servers combine into a personal research system that becomes more valuable over time. Part 5 of the Advanced Tier series.

Dec 2025 · Methodology

Creating Helpers: When to Delegate Work

When to create separate Claude Code helpers for focused work, how to design tasks that are easy to hand off, and patterns for running multiple helpers at the…

Dec 2025 · Methodology

The Cold Start Problem: Why the First Five Minutes Matter Most

Why the first five minutes of an AI coding session matter most, and how a CLAUDE.md context file solves the cold-start problem before work begins.

Dec 2025 · Methodology