Where a child is born sets a thirty-year gap in life expectancy before a single choice is made. Global health has no shortage of actors or effort; money, incentives and accountability simply flow in different directions, and only about a third of the signal in raw data ever reaches a decision intact.

Public health, financing and outcome data reconciled into one model, then challenged by four AI models for gaps and overclaiming before any chart was drawn. The Lusaka Agenda's five official shifts are wired into the budget so the reader can test them, not just read them.

Which decisions matter is a judgement from fifteen years inside these institutions, not a statistic: the piece names where leverage sits, from vertical programmes to primary care, from clinic to city design, and refuses to average what is not the same.

Allocate a USD 3.2B budget and watch equity, resilience and sustainability move. Drag a community toward isolation and read the risk in cigarette-equivalents. Redesign a city and see which real place it resembles. Every chapter ends with the same question: what would change your mind?

A network of 150 offices ordered USD 3.25B through 160,550 purchase orders in a year; 54% of them are under USD 5k and carry 5% of the value. Standard BI shows the transactions. It does not say where to look first, or which number can be trusted.

The spend-mapping and office-clustering method I built by hand inside a global institution from 2012, rebuilt with AI as an agency-neutral engine: a five-mark scorecard (fit, efficiency, price, resilience, local economy) against 150 peers, with every finding opening its chart, its table and its method, in that order.

Everything is shown as a signal to review, never as a finding. Forecast and realised savings are never added together. The controller decides; the system ranks and shows its rule, so the decision can be defended to an audit committee later.

Start from the network, an office or a theme, pick a year and compare against the five bureaus. Three things stand out against peers; everything else is in order. Built for the question oversight actually asks: where should we look first, and why.

Arrivals returned above the 2019 peak, so the story looked like recovery. The trap: volume came back, behaviour didn't. The real question isn't how much travel recovered, but what broke and stayed broken.

ChatGPT, Gemini and Grok produced independent versions for comparative review, structured disagreement, not one source of truth. Claude held the architecture and ran visual validation before deploy.

The thesis, tourism doesn't bounce back, it mutates, is a judgement, not an output. Every claim is tiered by hand: Official, Derived or Proxy, with a confidence score the viewer can inspect.

Eight linked modules let a decision-maker do, not just read, and open the Evidence Drawer on any claim to see its source, tier and confidence. Nothing asks for blind trust.

193 nations, 150 years, 25 indicators across incompatible sources. Most development stories cheat: one chart that confirms the author's prior, frozen and called a trend. The trap is the single axis.

Dozens of authoritative datasets ingested through an automated pipeline and reconciled into one model: 194 countries × 25 indicators × 150 years. Every weaker indicator is flagged, not hidden.

Twenty-five indicators is a curation, not a dump. Secondary sources are marked, and every projection to 2050 is labelled projections, not commitments. Showing where data is modelled is the judgement.

Ask your own question of 150 years of data, press play, and inspect every indicator's source and coverage in Methodology & Sources, and know exactly how much each answer rests on.

A 4.8× recommendation looks robust on paper. Then reality intervenes, and the biggest number is often the one whose model is most wrong in your favour. The optimizer's curse.

Each of four parameters is estimated from imperfect evidence. The tool runs a hundred scenarios and maps the entire parameter landscape, the disagreement between the optimistic number and the realistic spread is made visible.

Knowing where a model breaks in the field isn't in the model. Twenty years across major UN agencies, procurement, supply chain, public health, is what flags the fragile assumption first.

Drag four sliders and watch a recommendation flip between Holds and breaks in real time. A funder sees, before committing, exactly which assumptions their confident number rests on.

Ninety-six years, results, hosts, economics, governance scandals, carbon, scattered across primary documents and contested estimates. Most tellings quote one tidy cost that averages a stadium bill and a national infrastructure programme as if they were the same thing.

Here the orchestration is of sources, not models. Every figure checked against primary documents. FIFA accounts, the Parliamentary Budget Officer, DOJ indictments, Our World in Data, and carried at its true confidence. Four tiers: Official, Estimate, Modelled, Snapshot.

The discipline is refusing to average things that aren't the same. The 2026 carbon footprint is shown as a range, no official figure exists. The uncertainty is part of the story, not an embarrassment to smooth over.

The flagship, The Ledger, asks who really pays, every figure sourced and labelled. Alongside it: Global Atlas, Outlier Hunter, The Mirror, a 3D Penalty Shootout. Proof the method scales into a beloved subject, and still refuses fake precision.

Hundreds of sites across inconsistent registers, many of them ruins, a share of them private. Lists existed; a way to see the pattern of a thousand years on one map did not.

Heritage registers and open geodata reconciled into one dataset, dated and tiered by source quality, with 412 sites marked as still to investigate rather than placed with false precision. Zoom out and the same engine shows 29,660 castles across 39 countries.

What to show by default is the curation: documented sites lead, uncertain ones are flagged, and the computed coverage (19.6% of the territory within 15 km of a castle in 840, 98% by 1240) is labelled as an estimate.

Proof that the method travels. An audience with no interest in procurement explores evidence the same way a board does: change the century, the style or the map, and watch the territory answer.