The First Agentic Navigator
Evidence essay · Signed commentary, not a badged data claim
This one is a personal note, not a data claim, so I am signing it. Every other essay on this site stands on a source registry; this one stands on thirty years of watching what institutions do when a fact is too expensive to check — and on the two years since that changed.
FAND is the third generation of a navigator I have been building for a long time. The first, FIND, the First Integrating Navigator for Development, linked the World Bank’s development databases to word-oriented Country Briefs in the 1990s and led directly to Monitoring Environmental Progress. The second, SDRPrep (Sustainable Development Review Preparation), built with CSR QuickStart at Gaia Metrics, carried the same framework into corporate and government sustainability reporting. Each generation reached for the same pairing, the number and the narrative behind it, and each stopped where the narrative became too expensive to check. (FAND in the glossary.)
The habit is older than any of them. I was born a week after Normandy, while the real work of Bretton Woods was under way in Atlantic City, and some of my early mentors had been there. When the IMF and I both turned twenty, I joined it as a “knowledge broker” between systems experts and economists. That began three decades of designing and managing decision-support systems at the IMF and the World Bank, from the Fund’s monitoring system for international banking to the Bank’s overhaul that became DataBank, and finally MEP. I have now spent as long outside. I took early retirement the year MEP was published because the work convinced me that our democracy requires more bottom-up decisions. (The founders’ story, and the career in one table.)
Theodore M. Porter was an early influence. His Trust in Numbers (1995) explains why central authorities lean on numbers: numbers travel across distance without the local knowledge that produced them.1 He later named that kind of surface a thin description,2 and that is what the MEP balance sheet was. A thin description earns trust only if the thick detail behind it can be produced on demand. The Framework is built around that test, and the glossary keeps the distinction.
After MEP I went deeper into what I call the four H’s. Each answers a question the 1995 accounts left open:
- Hollerith, on why measurement went thin. The 1890 Census adopted his punch-card tabulator, and processing became cheap while contextual quality control did not.3 See the Hollerith Pivot and The Ledger of Consent and the 1890 Break.
- Hohfeld, on what the accounts leave out. Every legal relationship is one of eight positions in four correlative pairs, and the System of National Accounts reads only the first.4 See Hohfeld’s missing columns and OG-011.
- Hotelling, on what an exhaustible resource is worth in the ground and over what horizon its rent should be capitalized.5 See how FAND and CWoN measure natural capital.
- J. R. Hicks, on Fundist against Materialist: value the going concern by capitalizing its income, rather than summing the objects one can list.6 See Three types or four.
All four point to the same wall.
For most of my career, the binding constraint on economic analysis was never theory. It was reading. A country desk officer, a debt-crisis mission, a wealth-accounting exercise like the one I ran in 1995 — every one of them ran into the same wall: there is a mountain of qualitative record behind any number worth trusting, and no institution can afford to read all of it, so it samples. It picks the capital cities, the flagship indicators, the countries with the best statistical offices, and it extrapolates from there. The extrapolation is not dishonesty. It is what you do when reading is the scarce resource.
Frontier models changed which resource is scarce. Claude and its peers did not make institutions smarter about economics — the theory hasn’t moved. What moved is the cost of reading everything: every administrative filing, every footnote, every country’s own accounting convention, checked against the next country’s, at a marginal cost close to zero and with a session log that shows exactly what was checked and how. That is a different kind of change than a faster spreadsheet. It removes the reason to sample.
FAND is the claim, applied
The name is not a coincidence. FAND — the First Agentic Navigator for Development — is what this site is built on, and it is also the argument: agentic AI applied directly to the machinery of national accounts, not as a chatbot bolted onto the old workflow but as the research partner that makes a wider ledger affordable in the first place. The scale of it — 200+ of the 237 economies and 3,258 US counties, on one closed identity — is not a productivity anecdote. It is what changes when a single economist can direct an agent through hundreds of logged, checkable sessions instead of managing a department that can only afford to look closely at a fraction of the world.
| Sampling era (my 1995 capstone) | Full-read era (FAND, 2025–) | |
|---|---|---|
| Coverage | Select flagship countries and indicators | 200+ of 237 economies, 3,258 US counties |
| Why the gap existed | Reading and reconciling records was a department’s worth of labor | Marginal cost of one more county is an agent-session, not a hire |
| What backs a number | Institutional memory, expert judgment | A source registry and a reproducible, re-runnable pipeline |
| What happens to the footnote no one had time to check | It stays a footnote | It becomes a line, or a disclosed gap |
What this changes for the reader, not just the builder
If you sit in a governance or investment seat, the practical shift is this: “we didn’t have the analyst-hours to check that” stops being an acceptable answer, because the analyst-hours it used to cost no longer gate the check. Audit and replication — historically the parts of institutional analysis that got cut first when budgets tightened — get cheaper faster than the analysis itself does, because verifying a claim an agent already traced is easier than generating the claim was in the first place. That inverts an old institutional habit of trusting the summary and skipping the trail.
None of this is a claim that the model does the judgment. It doesn’t decide what a substantive right is worth, or which uncertainty band is honest — that is still the economist’s call, made and re-made across the session log this site keeps. What changed is only the reading. But reading was the wall. I spent thirty years on the other side of it, and I did not expect to see it move in my lifetime.
— John C. O’Connor
Footnotes
-
Theodore M. Porter, Trust in Numbers: The Pursuit of Objectivity in Science and Public Life (Princeton University Press, 1995). ↩
-
Theodore M. Porter, “Thin Description: Surface and Depth in Science and Science Studies,” Osiris 27, no. 1 (2012): 209–226. ↩
-
Leon E. Truesdell, The Development of Punch Card Tabulation in the Bureau of the Census, 1890–1940 (US Government Printing Office, 1965). ↩
-
Wesley Newcomb Hohfeld, “Some Fundamental Legal Conceptions as Applied in Judicial Reasoning,” Yale Law Journal 23 (1913): 16–59. ↩
-
Harold Hotelling, “The Economics of Exhaustible Resources,” Journal of Political Economy 39, no. 2 (1931): 137–175. ↩
-
John Hicks, “Capital Controversies: Ancient and Modern,” American Economic Review 64, no. 2 (1974): 307–316. ↩