WOLF AI field guide
FCA case-intelligence software, defined.
FCA case-intelligence software organizes evidence, dates, actors, allegations, and source passages for plaintiff-side False Claims Act and qui tam teams. WOLF AI is an early-stage example built around source-linked, attorney-reviewed work product.
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
The Department of Justice reports that whistleblowers filed 1,297 qui tam lawsuits in fiscal year 2025, the highest number in a single year and a sharp rise on the previous record of 980 set in 2024. Those filings drove more than $5.3 billion in reported settlements and judgments.
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
Who is this workflow for?
Plaintiff-side FCA and qui tam teams — relator counsel, boutiques, and the whistleblower practice groups inside full-service firms — who are deciding whether a workflow-specific tool sits usefully between their document store and their drafting.
When it is the wrong tool. It is not the right category if the problem is collection, preservation, processing, or production across a large dispute portfolio: that is eDiscovery. It is also not the right category if what is needed is legal research, an opinion on whether conduct is actionable, or a filing decision.
What documents and inputs do you need?
- PDFs of medical records, billing exports, claims data, compliance policies, correspondence, memos, and scanned paper handled with OCR.
- The matter frame the legal team already has: custodians, entities, date range, and the conduct being examined.
- Formats other than PDF need converting first. Native CSV and DOCX ingestion is on the roadmap and is not represented as shipped.
How does the workflow actually run?
- 1.Create a structured matter workspace and ingest supported documents.
- 2.Identify relevant passages, people, organizations, dates, and claimed conduct.
- 3.Build editable chronologies and claims maps that retain document, page, and passage provenance.
- 4.Export work product only after an attorney reviews and approves it.
What does this look like in practice?
Illustrative scenario
Illustrative only — a constructed scenario, not a customer matter. A relator brings roughly 4,000 pages: two years of billing exports as PDFs, a folder of clinical notes, and an email thread with a compliance officer.
- The documents land in one matter workspace, tagged by source, custodian, and date, so nothing is identified only by a filename.
- Review surfaces candidate passages — a service code appearing on dates a clinician was not on site, and a compliance email acknowledging the pattern.
- Each candidate keeps its document, page, and passage reference, so an associate can open the underlying record rather than trusting the summary.
- The associate rejects two thirds of the candidates as noise, keeps the rest, and the partner reads a chronology in which every entry is clickable back to the page it came from.
What this does not show. Nothing in that sequence establishes falsity, knowledge, or materiality. It establishes where the documents are and what they say.
What do you get out, and who reviews it?
- A structured matter workspace with tagged, searchable source documents.
- An editable, source-linked chronology draft.
- A claims map connecting proposed allegations to specific passages.
- Every one of those is a draft. Counsel owns reviewing, correcting, and approving it before it is used anywhere.
Where does this approach break down?
- WOLF AI does not determine whether conduct violates the law.
- Current document support is PDF-first; native CSV and DOCX ingestion is not represented as shipped.
- The product is in an early design-partner stage and does not replace legal research or attorney judgment.
- No verified public time-savings study has been published. Efficiency statements on this site are stated hypotheses, not measured results.
Common questions
How is case-intelligence software different from eDiscovery?
eDiscovery platforms are generally built around collection, processing, search, review, and production across many kinds of dispute. Case-intelligence software is narrower: it structures the facts of one matter into work product — chronologies, claims maps, damages inputs — for a specific practice area.
Does it write the complaint?
No. It organizes source material and proposed claims into a complaint-support packet. Drafting, theory, and filing decisions stay with counsel.
What does source-linked actually mean here?
Every proposed entry carries the document, page, and passage it came from, so a reviewer can open the original record instead of accepting a generated statement on trust.