Black Swan Causal Labs
Notes from Black Swan Causal Labs

Writing.

On causal reasoning, AI in research,
and the craft of building better evidence.

The NHANES Results Explorer showing hypertension prevalence among US adults, with estimates matching NCHS Data Brief 511
Featured essay / Data & tools

A proof of concept: an open-source MCP server that lets an agentic AI assistant analyze NHANES the way NCHS does, checked against published estimates.

Read the essay

All writing

05 essays / Newest first
Data & tools

Bring the Data to the User

An NHANES MCP server that gets the survey weights right, validated against published NCHS estimates, and what the pattern means for registries, EHR and claims data.

AI in research

The Delta: From AI-Naive to AI-Fluent

Why domain expertise—and a willingness to experiment—can be the starting point for useful AI in pharmacoepidemiology.

AI in research

Is Prompt Engineering Dead?

Four prompting strategies, two model families, one research task. What changes when models interpret more of your intent?

Agent design

AI Agents and Idiot Sandwiches

What a kitchen brigade can teach us about dividing work, preserving context, and building AI systems for research.