Latest,
Evaluating intelligent systems honestly
Matching pipelines, scoring models, and agentic systems all fail on the same class of case: the messy one a tidy demo never shows you.
Read the noteNotes from the lab
Short pieces on agents, applied ML, evaluation, and the production constraints that shape our research.
Archive
Ontology-based financial intelligence: structure before signal
Ad-hoc scraping gives you text about the market. An ontology gives you a structure you can query, reason over, and eventually act on.
Synthetic test data that fits your pipeline: formats and an API
Test data is only useful where your pipeline can read it. Export formats and a programmatic API matter as much as the data itself.
Record-linkage testing needs messy data, not clean rows
Entity resolution systems are scored on the duplicates they catch and the false merges they avoid. A test set of unique, well-formed rows cannot exercise either.
Why Faker fails entity resolution (record matching) tests
Generic fake data looks fine in demos and breaks when you test record matching systems. Here is what entity resolution evaluation harnesses actually need from synthetic test data.