Brian James Curry·Jun 15Bringing It Home: How an American Sovereign Fund Undoes the Great ExtractionFor thirty years, globalization moved the gains to multinational margins and the costs to American workers and towns. The sovereign fund…
Brian James Curry·Jun 13The One-Time Bill: America Is Paying Once to Stop Renting the World’s Cheap LaborThe tariff price shock is a step, not a slope — a single adjustment back to honest prices after thirty years of consumption subsidized by…
Brian James Curry·Jun 12America Went Back to Hamilton — and It’s WorkingTariffs, subsidies, public credit, and now equity stakes: the U.S. has quietly reassembled its founding economic playbook. Here is the…
Brian James Curry·Apr 25Agentic AI Systems: From Memory to AutonomyIn the previous article, retrieval was a one-shot transaction. A user asked a question, the system pulled context, the model wrote an…
Brian James Curry·Apr 24Retrieval-Augmented Generation Done Right: Architecture, Pitfalls, and What Most Teams Get WrongThe RAG demo works. You ask a question, the system pulls a relevant passage from your documents, the model writes an answer grounded in…A response icon1A response icon1
Brian James Curry·Apr 5Drawing the Map: DAGs and the Backdoor Criterion (Part 2)This is Part 2 of a series where we walk through causal inference end-to-end. In Part 1, we defined a precise causal question — “what is…
Brian James Curry·Apr 4Before You Model Anything: Defining the Causal Question (Part 1)This is Part 1 of a series where we walk through causal inference end-to-end — with real code, real pitfalls, and the kind of analysis…A response icon1A response icon1
Brian James Curry·Apr 3The Finance Plumbing: Following a Dollar Through Wall Street’s Toll BoothsPart 2 of the Economic Plumbing series — A pipe-by-pipe breakdown of who takes what
Brian James Curry·Mar 29Running the Graph: How to Audit, Measure, and Orchestrate a Human–AI OrganizationA practitioner’s guide to turning network theory into network operations
Brian James Curry·Mar 28The Olorin: The Human That AI Was Built to RewardWhy the Most Dangerous Myth in AI Is That Anyone Can Use It Equally Well
