Open-web investigation
Locating primary documents across government portals, institutional databases, PDFs and archives.
Web research • Fact-checking • AI evaluation
I investigate difficult open-web questions, verify them against primary sources, and document the reasoning so anyone can audit it.
Locating primary documents across government portals, institutional databases, PDFs and archives.
Separating evidence from assumption, and recording the exact locator behind every claim.
Auditable evidence chains, search logs and clean JSON deliverables another person can reproduce.
Ten completed benchmarks across history, space, law, politics, technology, culture, science, economics and public records — each with a fixed answer and a full evidence trail.
AIBRC-001 · Public records and administrative history
A short, verifiable answer hidden behind legislative, administrative, geographic and census clues, with the two search shortcuts found in validation disclosed.
Read the case studyIndependent Demonstration Project — Not Client WorkAIBRC-001 · History of technology
A completed, fully sourced browsing benchmark built around the 1858 transatlantic telegraph cable, with independently checkable clues and a reproducible evidence trail.
Read the case studyIndependent Demonstration Project — Not Client WorkAIBRC-002 · Space mission records
A second completed browsing benchmark on a different domain: a space-mission question answered entirely from NASA records, including a technical flight-data PDF.
Read the case studyIndependent Demonstration Project — Not Client WorkAIBRC-003 · Legal case records
A third completed benchmark in a legal domain: a court-judgment date recoverable only from law reports, a judgment transcript and national archive catalogues.
Read the case studyIndependent Demonstration Project — Not Client WorkAIBRC-004 · US court records
A legal-records benchmark where the famous date is the wrong answer: the task is the first oral argument date of a consolidated 1950s appeal, printed only in the official reporter.
Read the case studyIndependent Demonstration Project — Not Client WorkAIBRC-005 · Politics and treaties
A politics benchmark built on treaty records: the signing date is famous, the date the instrument actually took effect is not, and both are documented by the depositary.
Read the case studyIndependent Demonstration Project — Not Client WorkAIBRC-006 · Technology history
A technology benchmark where the widely cited month is wrong and the correct day depends on which time zone the log is read in.
Read the case studyIndependent Demonstration Project — Not Client WorkAIBRC-007 · Culture and museums
A culture benchmark on a famous museum theft, built so that the holding institution corroborates the actors while the day-level date must come from a second, checkable record.
Read the case studyIndependent Demonstration Project — Not Client WorkAIBRC-008 · Science and publishing
A science benchmark that asks for a journal issue date rather than a discovery date, so the famous year and the Nobel year both act as traps.
Read the case studyIndependent Demonstration Project — Not Client WorkAIBRC-009 · Economics and central banking
An economics benchmark that separates the day a central-banking statute was signed from the day the twelve regional banks actually opened, using the system's own records and a 1914 Treasury announcement.
Read the case studyOther work of mine that is online today.
kudorabeauty.com
Booking site for barbers, salons and laundry professionals, serving customers at home, in the office, or in a hotel or Airbnb.
Visit sitevoltamarket.com
Marketplace project. The domain currently shows a registrar holding page rather than the site, so there is nothing live to view yet.
Visit site