WOLF AI field guide
Qui tam case management software.
Qui tam case management software organizes the documents, actors, dates, and allegations inside a False Claims Act matter. It is a narrower category than firm-wide case management, which runs intake, calendaring, and billing across every matter a practice handles.
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?
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
Under 31 U.S.C. § 3730(d), a relator receives at least 15 percent but not more than 25 percent of the proceeds when the government intervenes, and not less than 25 percent and not more than 30 percent when it declines and the relator proceeds alone. The Department of Justice describes the typical range as 15 to 30 percent.
Who is this workflow for?
Plaintiff-side firms whose False Claims Act and qui tam work has outgrown a shared drive and a spreadsheet, and who are trying to work out whether the answer is a firm-wide case management system, an eDiscovery platform, or something scoped to the matter itself.
When it is the wrong tool. It is not the right category if what the practice needs is client intake, conflicts checking, calendaring, trust accounting, or billing. Those belong in a firm-wide case management system, and no amount of matter-level structure substitutes for one.
What documents and inputs do you need?
- The matter document set as PDFs: billing exports, clinical or program records, contracts, correspondence, and scanned paper handled with OCR.
- The matter frame counsel already works from — custodians, entities, the period, and the conduct being examined.
- The allegations as currently drafted, even in rough form, so evidence can be attached to something specific rather than to a theme.
- Formats other than PDF need converting first. Native CSV and DOCX ingestion is on the WOLF AI roadmap and is not represented as shipped.
How does the workflow actually run?
- 1.Open one matter workspace and ingest the supported documents, tagged by source, custodian, and date.
- 2.Identify the actors, entities, dates, and claim references that appear across the set, and normalize the name variants between billing systems and correspondence.
- 3.Build the chronology and the claims map so each entry names the document, page, and passage behind it.
- 4.Track what is missing as explicitly as what is present, and have counsel review, correct, and approve every output before it is used.
What does this look like in practice?
Illustrative scenario
Illustrative only — a constructed scenario, not a customer matter. A boutique carries four active qui tam matters, and the largest is roughly 9,000 pages across billing exports, service logs, and two custodians’ email.
- Each matter gets its own workspace, so a document collected for one is never quietly reused as support in another.
- Within the large matter, claim lines, service logs, and the compliance thread are aligned by date and provider rather than by the folder they arrived in.
- The chronology draft carries 140 entries. An associate rejects 90 of them as noise in two sittings, because rejecting an entry means opening the cited page rather than re-reading a file.
- The 50 that survive are the ones a partner reads, and each one is clickable back to the record it came from.
What this does not show. None of that decides whether the conduct was knowing, false, or material. It decides where the documents are, what they say, and which allegations currently have nothing attached to them.
What do you get out, and who reviews it?
- One structured workspace per matter, with tagged and searchable source documents.
- An editable, source-linked chronology draft.
- A claims map connecting each proposed allegation to specific passages, actors, and transactions.
- An explicit list of gaps: allegations with no attached support, and claim lines with no corresponding record.
- All of it is draft work product. Counsel owns reviewing, correcting, and approving it.
Where does this approach break down?
- This category does not replace firm-wide case management, and WOLF AI does not offer intake, calendaring, or billing for the practice.
- It does not replace eDiscovery. Collection, preservation, processing, and production stay where they already are.
- Document support is PDF-first today; native CSV and DOCX ingestion is not represented as shipped.
- WOLF AI is early-stage, has no public production API or MCP server, and has published no verified case study or measured time-savings result.
Common questions
Is qui tam case management software the same as legal case management?
No, and conflating them is the most common mistake in this evaluation. Firm-wide case management runs the practice — intake, deadlines, documents, billing — across every matter. Qui tam case management software works inside one matter, structuring evidence into chronologies, claims maps, and damages inputs.
Do we still need our eDiscovery platform?
Yes, if you have discovery-scale data. Collection, preservation, processing, and production are a different problem, and WOLF AI is not represented as covering any of them. The two are complementary rather than alternatives.
What actually comes out at the end?
Editable, source-linked draft work product: a chronology, a claims map, a damages population with its assumptions written down, and a complaint-support packet. Every entry names its document, page, and passage so a reviewer can check it rather than trust it.