Data Journalism =============== Type: Systems Organization: Enigma Dates: 2025-26 Topics: Agent workflows, Data journalism, Databricks, DuckDB, Marimo, RECAP, Entity resolution Summary ------- An agentic research pipeline for data journalism: reusable queries, entity resolution, and human review, with published investigations as worked examples rather than the main exhibit. Project Notes ------------- The main work was not a sequence of one-off stories. It was a research system for data journalism: how to ask questions of a large entity graph, keep the path from source to claim inspectable, hand intermediate results between sessions and tools, and keep a person responsible for judgment before anything published. I built that pipeline from warehouse queries through local analysis (Databricks, DuckDB, Marimo) and into agent-assisted research workflows that reused the same checks and criteria across topics. The aim was modest and operational: preserve method across sessions, including what was queried, what a result meant, which verification steps had run, and when a human still had to decide. The public investigations listed below are outputs and stress tests of that system, published under Enigma’s institutional byline. They follow shell companies, mass litigation, licensing carve-outs, and jurisdictional patterns, but they are best read as evidence that the pipeline could carry a story from raw records to a publishable claim. Specific counts and case examples (for instance Schedule A litigation in RECAP, or state registration data joined to federal licensing) live in those pieces; the durable product of the work is the method underneath them. A separate, unpublished reproduction of the NYC Public Advocate’s worst-landlords methodology came within roughly 15 percent of its published counts. It was a deliberate dry run of the same pipeline against open data, not a public ranking. Related systems work at Enigma (reusable research skills, entity-resolution clients, and multi-model evaluation) is described under Content Engineering at Enigma. Original and Related Work ------------------------- How Much Is a Verification Worth? Read an investigation estimating the economic value of a single identity verification from Enigma data. https://www.enigma.com/resources/blog/enigma-newsletter-how-much-is-a-verification-worth How to Sue a Company That Doesn't Even Exist Read an investigation of mass-defendant lawsuits against businesses that appear not to exist. https://www.enigma.com/resources/blog/enigma-newsletter-americas-most-sued-companies-dont-exist Anatomy of a Shell Company Read an investigation of the addresses, agents, and officers that reveal shell-company networks. https://www.enigma.com/resources/blog/enigma-newsletter-anatomy-of-a-shell-company Wyoming's Corporate Boom Read an investigation of the state structures that make anonymous business ownership a paid feature. https://www.enigma.com/resources/blog/enigma-newsletter-wyomings-corporate-boom No Branches, No Verification, No Problem Read an investigation of a Colorado licensing carve-out and crypto-named money-service businesses. https://www.enigma.com/resources/blog/enigma-newsletter-no-branches-no-verification-no-problem The Geography of Corporate America Read a data-driven map of where American companies incorporate and why those jurisdictions attract them. https://www.enigma.com/resources/blog/enigma-newsletter-geography-of-corporate-america Canonical page: https://charlesberret.net/projects/#data-journalism Plaintext: https://charlesberret.net/projects/data-journalism.txt