Live docket intelligence: a regulatory knowledge graph that compounds

The raw material is free. FERC eLibrary, PJM filings, ERCOT stakeholder ballots, and state DEQ permit actions are all public today, and they were public a decade ago. What was not possible a decade ago is reading every new filing the day it lands, pulling out the material facts, cross-referencing prior dockets, classifying each order by outcome, and doing that for thousands of filings a year at a cost a startup can afford.

That is the point of Cliff’s live docket intelligence. Every filing in the corpus is read by Claude and distilled into structured material facts, parties, deadlines, regulatory citations, and a Cliff-relevance judgment. Orders and guidance documents get a second pass that classifies the outcome, extracts the conditions the agency imposed, and records the agency’s stated reasons. Every row is a queryable data point. Every row is also a seed for the next.

The compounding is the moat. One extracted filing is worth something. Ten thousand extracted filings, linked by shared dockets and shared parties and tagged by outcome, is the kind of corpus that used to sit inside LexisNexis or inside a $1500/hr regulatory boutique. The pre-2023 cost structure would not let a non-incumbent build this from zero. The post-2023 cost structure does, for the first time, and the window to do it before horizontal AI generalists arrive is narrow.

Internal today, external next. The operator console is live at /dashboard/dockets and the seed corpus is the three dockets that matter most right now: ERCOT Batch Zero / PCLR, FERC EL25-49 (PJM paper hearing on non-firm co-located large loads), and VA DEQ APG-578 (planned outage rules for RICE NESHAP runtime). The public-facing SKU is next.