Legal Current Law
Is your AI citing the most recent law?
Sometimes a Supreme Court ruling gets thrown out by a later one — Roe by Dobbs in 2022, Chevron by Loper Bright in 2024. After that happens, citing the old case as if it's still law is malpractice. This pack runs your AI through legal-research questions and flags any response that cites an overruled case without acknowledging the overruling.
Highlights.
Every overruling record verified against CourtListener's citator — no hand-typed facts
Covers 14 landmark SCOTUS overrulings: Chevron/Loper Bright, Roe+Casey/Dobbs, Lemon/Kennedy, Quill/Wayfair, Abood/Janus, Plessy/Brown, Apodaca/Ramos, Bowers/Lawrence, Austin/Citizens United, Booth/Payne, NL Cities/Garcia, Wolf/Mapp, Pace/Loving
Deterministic — case-name substring + Claude-extracted alias matching + acknowledgment-keyword detection, no LLM judge at run time
Cache primed out-of-band (worker/scripts/prime_overrulings.py); re-runs are byte-identical
Scope: seven landmark SCOTUS overrulings; not a full Shepardizing replacement
Bar-licensed attorney sign-off pending (Phase L-5)
Vertical harnesses
are co-built.
Vertical harnesses ship with regulator-grade signed reports, hand-labeled fixtures, and per-customer calibration. We co-author them with one design partner per vertical and the rest of the catalog rolls out as paying customers pull them.
Example checks.
Acknowledges Chevron was overruled
Cites Chevron as if it's still good law
Judging criteria.
What a pass means
A pass means the agent either cites only cases that are still good law, or flags any overruled case it cites with explicit language ("overruled by", "no longer good law", "abrogated"). Citing Chevron without noting Loper Bright fails.
Data sources
- CourtListener citator
Free public US court-opinion database with a built-in citator. Every overruling in this pack is verified against CourtListener — case-cluster lookup, opinions-cited graph, and the overruling opinion's own text.