The closed-loop PI engine. Detect → CREB™ → CourtChain™ → Legal. Every 2 weeks. Automatic.
Your existing PI vendors (Cotiviti, HMS, EXL, internal) hand your SIU a flagged-claim spreadsheet. Your team then triages it, substantiates it, writes the referral, and hands it to legal. Weeks per case, on a sampling cadence. JIL Sovereign closes the loop: detect → AVA clusters → T2 auto-substantiates → CREB™ auto-generates → CourtChain™ anchors → auto-submits to your legal team's queue, biweekly, with the FRE 902(13)/(14) self-authenticating exhibits already attached. Hours per case, continuous cadence, your SIU's name on every docket. We take 10% of what your MCO actually recovers. If you don't recover, you don't pay the contingency.
Two commercial legs. Both customer-aligned.
The 10% contingency is the hero of this deal. JIL only earns the contingency on dollars your MCO actually recovers -- net of MAC appeal, settlement negotiation, and any pursuit. Industry-standard SIU contingency runs 15-25%. Outside counsel charges 33%. JIL is materially below market on the line item that matters most.
The flat fee covers the always-on infrastructure (T1 deterministic scan + AVA agentic clustering + T2 substantiation + AVA Pro escalation + T3 CREB™ + AVA Pro+ continuous monitoring) capped at a percentage of your CMS-disclosed program-integrity spend. The fee floor is predictable. There are no per-finding charges, no per-claim charges, no per-FTE add-ons, no per-vertical license expansion.
A career-positive force-multiplier
JIL is the back-office. Your SIU is the front line. Every case JIL surfaces enters your queue pre-substantiated. Your team approves, escalates, and takes credit on every CMS, OIG, MFCU, and DOJ FCA referral.
Your headcount stays. Your vendor stack stays. Your performance metrics climb 5-10× without a single org-chart change.
Statutory + fiduciary defense
42 CFR 422.503 (MA compliance program), 42 CFR 438.608 (Medicaid MCO FWA), ERISA §404 (fiduciary duty), SOX §404 (internal controls). One CourtChain™ anchor + FRE 902(13)/(14) self-authenticating CREB™ documents discharge of all four -- measurably, in court-admissible form, against a public CMS dataset.
When the OIG, state AG, or a qui-tam relator comes calling, you have receipts.
Budget predictability + upside alignment
flat fee at 12.5% of your CMS-disclosed PI budget -- predictable, auditable. Contingency at 10% of net cash recovered -- performance-aligned, customer-friendly. Both anchored to public data: 10-K + Schedule H disclosures + CMS PERM 2024.
One contract. One renewal cycle. One auditable invoice path.
Retro proves the system. Annual contract compounds it.
Year-1 starts with a one-time retro-active scan ($3.2M, UHG-scale) that builds the base dataset and proves the system on real Snowflake CMS data. The retro surfaces 4 years of accumulated unaddressed leakage in one pass -- that recovery wave realizes over Y1-Y3 as MAC appeals, DOJ FCA filings, and state recovery cycles complete. The annual contract (flat fee + 10% contingency) runs in parallel from day one, catching going-forward leakage on nightly cadence.
Both flows pay JIL the same 10% contingency on net cash recovered. Your MCO never pays for flagged-but-uncollected. JIL only earns on dollars that actually clear MAC appeal + settlement + recovery.
Pool sizing -- all CMS-public anchors
| Input | Value | Anchor |
|---|---|---|
| UHG annual medical-loss expense | $330B | UHG 10-K |
| CMS PERM 2024 improper-payment rate (MA) | 7.0% | CMS PERM 2024 report |
| Annual improper-payment loss pool | $23B | computed |
| Current SIU recovery (~9%) | $2B | UHG SIU disclosure |
| JIL-addressable annual unaddressed pool | $21B/yr | 91% of CMS PERM pool |
| 4-year retro pool (SOL/staleness-weighted) | $49B | ~2.35× annual, accounting for Y-2/-3/-4 decay |
3-year projection -- Target scenario (25% capture rate)
| Line item | Y1 | Y2 | Y3 | 3-yr cum. |
|---|---|---|---|---|
| Retro recovery realized (33% / 40% / 27% of $12.3B retro pool) | $4.04B | $4.92B | $3.31B | $12.27B |
| Going-forward recovery realized (50% / 75% / 100% of $5.25B/yr) | $2.63B | $3.94B | $5.25B | $11.82B |
| Total MCO recovery realized | $6.67B | $8.86B | $8.56B | $24.09B |
| JIL retro-active scan (one-time) | $3.2M | -- | -- | $3.2M |
| JIL flat fee (12.5% × $1.4B disclosed PI spend) | $175M | $175M | $175M | $525M |
| JIL contingency (10% × net cash recovered) | $667M | $886M | $856M | $2,409M |
| Total JIL revenue | $845M | $1,061M | $1,031M | $2,937M |
| MCO net benefit (recovery − JIL fees) | $5.83B | $7.80B | $7.53B | $21.16B |
| ROI on JIL spend | 6.9× | 7.4× | 7.3× | 7.2× |
3-year totals -- all three scenarios
| 3-yr cumulative | Conservative (15% capture) | Target (25% capture) | Aggressive (40% capture) |
|---|---|---|---|
| MCO recovery realized (Y1+Y2+Y3) | $14.44B | $24.09B | $38.50B |
| JIL retro scan + 3-yr flat fees | $528M | $528M | $528M |
| JIL contingency (10% × recovery) | $1,444M | $2,409M | $3,850M |
| Total JIL revenue 3-yr | $1.97B | $2.94B | $4.38B |
| MCO net benefit 3-yr | $12.47B | $21.16B | $34.12B |
| 3-yr ROI on JIL spend | 6.3× | 7.2× | 7.8× |
Capture rates anchored to portfolio data. JIL's existing 11-engagement portfolio on real CMS Snowflake data has already surfaced $29.5B at risk with $9.53B recovery high -- a ~32% capture rate against the surfaced pool, sitting between Target and Aggressive bands. The 15% Conservative band assumes only half of currently-surfaced findings clear MAC + appeal + recovery; the 40% Aggressive band assumes JIL Corridor cross-MCO joins are wired in by Y2 to multiply capture. Recovery realization curves (Y1 33%, Y2 40%, Y3 27% for retro; 50% / 75% / 100% for going-forward) reflect typical MAC appeal + DOJ FCA + state MFCU recovery timelines.
What stays the same. What gets force-multiplied.
The cleanest signal that this is not a vendor-displacement pitch: there's nothing in the JIL contract that requires you to change a single existing vendor relationship. Cotiviti continues. HMS continues. Optum-internal continues. Outside counsel continues. JIL runs parallel on a different surface area.
Your team, your vendors, your contracts
All existing PI relationships continue under their current scope. JIL operates on the architectural long-tail -- the cross-system joins your current stack was not built to run. Zero displacement. Zero RFP for the incumbents. Zero contract renegotiation.
Every case in your team's name
SIU receives pre-substantiated CREB™ packets. SIU approves the OIG SDP / DOJ FCA / state MFCU referral. JIL is acknowledged on the technical exhibit only -- never as relator, never as fact witness, never on the docket cover. Performance reviews recognize the SIU team.
Audit-defensible by construction
Every finding anchored to CourtChain™ + FRE 902(13)/(14) self-authenticating. When CMS, state AG, or a qui-tam relator asks "did you have a reasonable detection program?" the answer is verifiable, court-ready, dated, signed -- by the deterministic Tier-1 catalogue running every night across the entire claim universe.
What JIL catches that the current stack architecturally cannot.
These are not vendor failings. They are architectural gaps. The patterns below require multi-vintage joins across 5+ federal datasets running on the entire claim universe -- not on a vendor sample, not on a flagged subset.
| CMS PERM-cited pattern | Why no current vendor closes it | JIL closes it via |
|---|---|---|
| Multi-year recidivism (same NPI, 3+ program years) | Each program year is a separate engagement; nobody stitches across | AVA max-lookback rule; FCA scienter case built in one click |
| LEIE post-exclusion billing | No vendor runs 83K LEIE × 259M Part-D rows nightly | Snowflake compute · nightly LEIE × CMS Part-D cross-walk |
| CMRA / phantom-premise suppliers | Field investigation cost prohibitive at scale | USPS-CMRA registry + Lob.com CASS+DPV (live 2026-05-13) |
| Deceased-beneficiary billing | Single-case prosecution under-recovers; needs cohort scale | CMS deceased file × utilization cross-walk per program-year |
| PECOS-deactivated providers still billing | Cross-system reconciliation -- not in any SIU's job description | PECOS × NPPES diff overlay on every claim |
| DRG creep / upcoding drift over time | Year-over-year comparison requires multi-vintage joins | AVA agentic clustering across multi-year DRG distributions |
Why Cotiviti, HMS, and Optum-internal cannot close this loop.
This isn't a knock on the incumbents. They were built for rules-engine claim editing + sampled audits. They do that work well. What they cannot do -- architecturally, not for lack of effort -- is run the closed loop JIL runs every two weeks. The wedge is real, defensible, and load-bearing on the commercial model.
| Capability | Cotiviti / HMS / Optum-internal | JIL Sovereign |
|---|---|---|
| Detection cadence | Quarterly or monthly audits; sampling-based | Nightly Tier-1 scan across the entire claim universe; biweekly closed-loop legal submission |
| Detection surface | Rules-engine claim edits, DRG validation, COB/TPL, RAC-style overpayment | All of the above's leftovers -- multi-year recidivism, LEIE post-exclusion, CMRA / phantom-premise, deceased-beneficiary, PECOS-deactivated, DRG creep, CMS PERM-cited systemic patterns |
| Triage pipeline | Flagged-claim spreadsheet → SIU human review → substantiation → referral packet (weeks) | AVA agentic clusters → T2 auto-substantiation → CREB™ auto-generation (hours) |
| Evidence form | Flagged claim list with reason codes | FRE 902(13)/(14) self-authenticating CREB™ on CourtChain™ -- direct-to-court admissible |
| Legal hand-off | Manual SIU referral; legal team rebuilds the packet for filing | Auto-submit to your legal team's queue, biweekly, with referral packets pre-formatted for HHS-OIG SDP / DOJ FCA / state MFCU / MAC appeal |
| Coverage scope | Healthcare only · MA + Medicaid · post-payment | MCO + SNAP/Nutrition + Transportation + VA + Bank + Capital Markets -- same engine. Pre-settlement (Pillar 1) AND retro (Pillar 2) on one contract |
| Statute-of-limitations tracking | SIU manually tracks per case | CourtChain™ anchor timestamps + auto-alert before SOL expiry per jurisdiction (FCA, state Medicaid recovery, ERISA) |
| Data residency | Data shipped to vendor; vendor holds at rest | Runs inside your Snowflake / Databricks. JIL never holds your data at rest. SOC 2 inherits from your stack. |
| Pricing | 15-25% contingency on recovery, plus subscription/per-finding line items | 10% contingency on net cash recovered + flat fee at 12.5% of your existing CMS-disclosed PI spend |
The one-line summary. Cotiviti gives you a flagged-claim spreadsheet. JIL gives you a court-ready referral packet, every two weeks, anchored on an immutable ledger, auto-submitted to your legal team -- for less money, on customer-aligned contingency. Same SIU. Same vendor stack. Net new recoveries that didn't exist before.
Your SIU runs the show. We carry the math and the downside.
$1M flat onboarding, all-in. No per-finding charges during the pilot. JIL embeds 2 forensic analysts under your SIU's direction. Snowflake feed live in 5 business days. AVA workspace + CREB™ generation live in 10 days.
Pilot deliverables -- your SIU's name on every one:
- Day 30 -- 3 named cases, ≥ $5M expected recovery each, CREB™ court-ready, referral packets pre-formatted for HHS-OIG SDP / DOJ FCA / state MFCU
- Day 60 -- full AVA Pro multi-vertical scan complete · 10 cases in MAC submission · SIU dashboard live
- Day 90 -- measured Y1 capture rate against the $21B addressable pool · Tier-3 expansion plan committed
Asymmetric downside: if the 90-day deliverables miss, the $1M converts to a 6-month platform credit + contingency drops from 10% to 7.5% for the entire Y1 contract. No other vendor in MCO PI takes pure downside on the math.