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.
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.
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.
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.
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.
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.
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.
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).
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…
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…
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.
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.
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…
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.
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.
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.
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).
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.
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.
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.
Research Phases Need Different Prompts
Exploration, implementation, and documentation require different AI prompting strategies. Match the prompt to the phase.
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.
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.
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.
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.
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.
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…
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.