WOLF AI field guide
FCA legal analytics and case intelligence are not the same thing.
Legal analytics studies patterns across many cases — courts, judges, opposing counsel, timing, and outcomes. Case intelligence works inside one matter, structuring its evidence into chronologies, claims maps, and damages inputs. A plaintiff-side False Claims Act team usually has questions of both kinds.
Published · Last reviewed
Written and maintained by the WOLF AI product team and checked against the public sources cited on this page. It has not been reviewed by outside counsel, and it is not legal advice.
What do the numbers say?
According to the Department of Justice, False Claims Act settlements and judgments exceeded $6.8 billion in the fiscal year ending September 30, 2025 — the highest single-year total in the history of the statute. Settlements and judgments since the 1986 amendments now exceed $85 billion.
Source: DOJ: False Claims Act settlements and judgments exceed $6.8B in fiscal year 2025
Federal Rule of Civil Procedure 9(b) requires that a party "must state with particularity the circumstances constituting fraud or mistake." In practice that is what turns an FCA matter into a document-organization problem: the allegation has to name specific claims, dates, and actors, each traceable to a record.
Source: Federal Rule of Civil Procedure 9(b): pleading fraud with particularity
Of the more than $6.8 billion in False Claims Act settlements and judgments the Department of Justice reported for fiscal year 2025, over $5.7 billion related to matters involving the health care industry, restoring funds to programs including Medicare, Medicaid, and TRICARE.
Source: DOJ: False Claims Act settlements and judgments exceed $6.8B in fiscal year 2025
Who is this workflow for?
Teams evaluating tools described as False Claims Act analytics, litigation analytics, or plaintiff-side case intelligence, and finding that products under those labels do markedly different things.
When it is the wrong tool. WOLF AI is not the right tool for the analytics question. It holds no docket data, no judge or court data, and no outcome data, and it cannot tell you how a district has historically handled a motion.
What documents and inputs do you need?
- For case intelligence: the matter’s own documents, as PDFs, including scans handled with OCR.
- The actors, entities, period, and conduct under examination.
- The proposed allegations, and the statutory, regulatory, contractual, or program requirements counsel considers relevant.
- Nothing external. WOLF AI does not ingest docket data, case law, or outcome data, and does not hold a corpus of other matters.
How does the workflow actually run?
- 1.Ask which question you actually have: a question about the wider landscape of cases, or a question about the evidence in this one.
- 2.Route landscape questions to analytics products built on docket, judge, and outcome data, which WOLF AI does not hold.
- 3.Route evidence questions into structured case intelligence: chronology, claims map, damages population, each entry carrying its source location.
- 4.Keep counsel’s judgement between both kinds of output and any decision, because neither kind supplies it.
What does this look like in practice?
Illustrative scenario
Illustrative only — a constructed scenario. A team preparing a healthcare FCA matter has two open questions in the same week.
- The first is a landscape question: how has this district tended to handle particularity challenges in similar matters. That is analytics, and it needs docket and outcome data.
- The second is an evidence question: which of the twelve proposed allegations currently have a supporting passage attached, and which have none.
- The second question is answered inside the matter, from the matter’s own documents, and produces a claims map with four rows visibly empty.
- The four empty rows change what the team collects next. The analytics answer changes how they plead. Neither substitutes for the other.
What this does not show. A tool that answers one of those questions well and is bought expecting the other will look like a failure when it is simply a different product.
What do you get out, and who reviews it?
- A clear division between the analytics questions and the evidence questions on a matter, written down before anything is bought.
- From case intelligence: a source-linked chronology, a claims map, and a damages population with stated assumptions.
- An explicit gap list, which is usually the output that changes what the team does next.
- Counsel owns every legal determination, and no output here is one.
Where does this approach break down?
- WOLF AI performs no legal analytics: no docket data, no judge or court analytics, no outcome prediction, and no case law.
- It does not benchmark a matter against other matters, because it holds no corpus of them.
- Patterns visible inside one record set describe that record set, not a population, and are not statistical findings.
- The product is early-stage, PDF-first, and has published no verified case study.
Common questions
Does WOLF AI predict case outcomes?
No. It holds no docket data, no judge or court analytics, and no outcome data, and it makes no prediction about how a matter will resolve. Anything described as outcome analytics is a different category of product.
What does case intelligence mean here?
Structuring the facts of one matter — evidence, dates, actors, allegations, and source passages — into reviewable work product. The intelligence is about your record set, not about the wider landscape of litigation.
Can a pattern in the documents be used as evidence?
A pattern inside one record set is a question to investigate, not a finding. Whether it reflects conduct, documentation practice, or case mix is for counsel and qualified experts to determine.