Disclaimer: Independent product / portfolio work by Kaushal Khodifad. Not a live commercial product.return to portfolio
Disclaimer: Independent product / portfolio work by Kaushal Khodifad.
Lyzr · Agent Amadeo · BFSI

The dispute agent a Chief Risk Officer would actually approve.

An autonomous payment-dispute & chargeback resolution system built on Lyzr - six specialized agents that resolve a dispute end-to-end, know when to stop, and leave a replayable audit trail a Chief Risk Officer would approve.

Glass-box, governedAgent-nativeShips to production
~$15BProjected US card-dispute value, 2026
~146M disputes · volume rising >10%/yr at most issuers
~95%Of enterprise GenAI pilots show no measurable ROI
MIT 2025 - not the model; integration & governance
10 daysReg E provisional-credit clock
Hard deadline · multi-system · evidence-heavy
The whole path, one glance · then watch it run live
Open the live console →
Intake
Evidence
Fraud + OFAC
Risk score
Reason code
Settle + file
conf ≥ 0.95→ agent acts autonomously
< 0.95→ halts to a human

Risk-score is the visible fork: clear the 0.95 gate and it settles & files itself; miss it (or trip a ceiling / sanctions rule) and it stops for a human. Every step is sealed to a hash-chained audit ledger.

Why an agent - not RPA, not a chatbot

Disputes are where agents win the argument outright

RPA breaks

Robotic automation shatters the moment a screen or document format changes - and it can't reason about ambiguous evidence.

Chatbots can't act

A conversational bot can advise a customer, but it can't pull records across five systems, score fraud, or file a chargeback.

Agents reason, act, and escalate

A dispute is irreducibly multi-step, multi-system, deadline-bound, and human-in-the-loop - the textbook agentic workflow.

Built on Lyzr · Agent Studio

Six specialized agents, one orchestrator, a hash-chained audit

Dispute Manager
Orchestrator
AgentMeshSLA TimerRBAC
fans out to
Audit & Reporting
Seals every step
Audit LedgerExplainability Layer
Intake & Triage
Salesforce CRMEmail/Chat connectorPII Redaction
Evidence Gatherer
MeridianCore APIVROL / Mastercom recordsGroundedness
Fraud Detection
Fraud FeedOFAC ScreenFairness & Bias Manager
Risk Scoring
HybridFlow (structured ML)Reflection Mechanism
Policy & Decision
Rules EnginePolicy EngineGroundedness
Settlement & Filing
Meridian GLVROL / Mastercom filingOutput Guardrail
Managerial pattern · AgentMeshDeadline & policy logic = deterministic HybridFlowDeployable to bank VPC / on-premHover an agent to see what it touches
The wedge

Everyone can demo a dispute bot. This one ships to production.

Glass-box scoring

Every decision shows the confidence factors that built it - inspectable, tunable, defensible.

Tiered autonomy

Act / brief-a-human / mandatory sign-off. The agent knows when to stop - at 0.95, at the ceiling, on a sanctions hit.

Hash-chained, replayable audit

Every action, tool call, model, and guardrail event logged and sealed with a SHA-256 hash chain - replay (and tamper-test) any decision for a Reg E / SR 11-7 / RBI examiner.

Data sovereignty

Runs in the bank's own VPC with zero data egress, native PII redaction and groundedness.

$37 → $9
cost / dispute
75%
resolved autonomously
100%
Reg E adherence
1-3 wks
pilot to production

Watch a dispute resolve - and watch it stop.

Run a live case through six agents, see it auto-resolve at 0.95 confidence, then watch a $1,310 friendly-fraud case correctly halt to a human - with a hash-chained, replayable audit trail.

Open the live console

Synthetic concept demo. The engine below executes for real; connectors & the dispute book are simulated - every console tool call is badged exec or sim accordingly.

EXECUTES FOR REALexec
  • Decision engine + 0.95 autonomy gate (deterministic factors)
  • Filing rule engine: network windows, 3DS liability shift, small-dollar file floor, Reg E clock
  • Network-correct reason codes (Visa VCR vs Mastercard 48xx)
  • Idempotent GL journal (localStorage state write)
  • SHA-256 hash-chained audit ledger (verify / tamper-test)
  • LLM narration via OpenRouter when a key is set (labeled)
SIMULATED / AUTHOREDsim
  • Core banking, CRM, OFAC, fraud-feed, VROL/Mastercom connectors (results seeded)
  • The dispute book - synthetic, ~3:1 auto/escalate mix authored to exercise every outcome
  • Cost model ($37 manual / auto / escalated) + handle-time latency budget
  • “Pilot to production” timeframe is an estimate

↑ Independent product concept by Kaushal Khodifad. ResolveIQ is an independent product concept by Kaushal Khodifad; it is not a real company or a commercial product. It explores the autonomous payment-dispute resolution on Lyzr space. Not a live commercial product. Data is illustrative.

Return to portfolioOpen the live demo