Now available for card issuers & processors

Resolve Chargebacks
10× Faster with AI

DisputeIQ is an AI-native intake layer for credit card dispute operations. Multi-agent classification, adaptive evidence collection, and real-time completeness scoring — built for modern card issuers.

Visa & Mastercard dispute rules mapped
15 chargeback reason codes supported
Powered by n8n · Supabase
disputeiq.app/dashboard
● Live
Active Dispute Sessions ● 14 live
94%
Classify Accuracy
2.1m
Avg Intake Time
87
Avg Case Score
Cardholder Merchant Amount Category Score Status
J. Mitchell Netflix Inc. $15.99 Cancelled Sub 92 Complete
A. Patel Amazon MKTP $248.00 Not Delivered 71 Review
K. Torres Uber Technologies $94.50 Duplicate 55 In Progress
S. Williams Marriott Hotels $340.00 Hotel No-Show 88 Complete
AI Intake · Active Session
Hi! I see you want to dispute a $94.50 charge from Uber on Jul 14. I'll help build your case.
Can you tell me what happened?
Unauthorised Duplicate Wrong amount
I was charged twice for the same ride
Got it — a duplicate charge. Do you have the date of the original charge?
Case Completeness Strong · 72%
94%
Dispute Classification Accuracy
Across 15 chargeback reason codes
<3min
Average Intake Completion Time
vs 20–30 min with manual forms
8×
Reduction in Agent Handle Time
AI collects all required evidence
0 API
No-SDK Frontend Integration
Drop into any issuer portal
Product Capabilities

Everything a card issuer
needs to win disputes

DisputeIQ replaces brittle static forms with a conversational AI agent that knows exactly what evidence each dispute category requires.

🧠

Intake Classifier

Analyzes transaction context and cardholder language to assign one of 15 dispute categories with a calibrated confidence score. Can create the case record in Supabase on first contact.

Agent 1 →
💬

Adaptive Questioning Agent

Determines the single most important missing field and asks a short, customer-friendly follow-up — fact-aware, never repeating what's already known, capped at 12 turns per case.

Agent 2 →
📁

Dynamic Evidence Documentation

Reviews the completed intake and recommends 2–5 high-value supporting documents specific to the dispute category — cancellation emails, receipts, shipping confirmations, and more.

Agent 3 →
📊

Confidence & Completeness Evaluator

Scores every turn across 5 dimensions: category fit, intake completeness, response consistency, question relevance, and investigation readiness. Routes to the correct next agent.

Agent 4 · Orchestrator + Evaluator →
📋

Summarization Agent

Generates a structured 3-section brief — Reason for Dispute, Key Details Collected, and Current Status — from the full Q&A history. Ready for back-office review with no rewriting.

Agent 5 →
⚙️

Orchestrator

Coordinates all five agents in sequence every turn, maintains stateful conversation sessions, and routes outputs between agents — all in under a second per message.

Express · ESM · Sub-agent SDK →
Workflow

From card transaction
to submission-ready case

DisputeIQ guides cardholders through a structured intake flow — and every agent handoff happens invisibly in under a second.

1
Trigger

Cardholder Initiates

User taps Dispute on a transaction. Metadata is passed to the orchestrator instantly.

2
Classify

Intake Classifier

Assigns one of 8 dispute categories with a confidence score. Re-runs every turn as context grows.

3
Question

Adaptive Questioning

Picks the most critical missing field and asks a natural follow-up — never repeating what's already known.

4
Document

Evidence Documentation

Structures each answer into a formatted evidence record mapped to the correct chargeback field.

5
Evaluate

Score & Evaluate

Confidence & completeness evaluated 0–100. Submit unlocks at 80+.

6
Summarize

Case Summary

Summarization agent generates a structured dispute brief — ready for bank review or chargeback filing.

Live Demo

Watch the AI work
through a real dispute

A cardholder disputes a duplicate charge. Watch confidence classify it, completeness score build, and evidence collect — turn by turn.

🛡️ DisputeIQ · Intake Session
Netflix Inc. · $15.99
Jul 28, 2026 · Card ending 4821
Analyzing…
Type a message…
🧠 Confidence Score
0%
Identifying…
Waiting for context
📊 Case Completeness
0%
Weak
No evidence collected yet
📁 Intake Fields
Fields collected from cardholder appear here.
🛡️
🧠
Intake Classifier

Maps complaint + transaction to one of 15 dispute categories. Creates the case record in Supabase on first contact via tool call.

Agent 1
💬
Adaptive Questioning

Asks the next best follow-up — fact-aware, never re-asking answered questions. Max 12 turns, computes dispute amount where inferable.

Agent 2
📁
Evidence Gathering

Recommends 2–5 high-value supporting documents specific to the dispute category and conversation collected.

Agent 3
📊
Orchestrator & Evaluator

Scores 5 dimensions per turn, determines routing action (CLASSIFY → CONTINUE → EVIDENCE → SUBMIT → HUMAN_REVIEW), flags human review below threshold.

Agent 4 · runs every turn
📋
Summarization Agent

Generates a structured 3-section case brief — reason, key facts, current status — from the full conversation history.

Agent 5
🗄️
Supabase + n8n

n8n orchestrates the workflow. Supabase persists case state, turn history, scores, routing decisions, and the final intake summary.

n8n · Supabase · Webhook trigger
Multi-Agent Architecture

Five specialist AIs.
One seamless intake.

Instead of a single monolithic prompt, DisputeIQ uses five focused sub-agents — each an expert in exactly one job — coordinated by a stateful orchestrator. The result is higher accuracy, lower latency, and full auditability at every step.

📐
5-dimension confidence formula
Score = 0.30×category_fit + 0.25×completeness + 0.15×consistency + 0.15×question_relevance + 0.15×investigation_readiness. Human review flagged below 0.55.
🔀
Dynamic routing every turn
The Orchestrator evaluates and routes to CLASSIFY → CONTINUE_INTAKE → GENERATE_EVIDENCE → PROCEED_TO_SUBMIT or HUMAN_REVIEW — decided fresh each message.
🗄️
Persistent Supabase case state
Every turn is persisted — case JSON, follow-up history, scores, routing decisions, and the final intake summary — surviving restarts and enabling audit trails.

Built with

n8n Workflow
AI Language Models
Supabase
Webhook API
Get In Touch

Let's build something for your dispute operations

Whether you're a card issuer looking to automate intake, a fintech exploring AI-powered chargeback tooling, or a product team evaluating this architecture — reach out. Happy to demo, consult, or collaborate.

📧
Email
appana.teja@gmail.com
🤖
Project
DisputeIQ — Dispute Intake Assistant
Response time
Typically within 24 hours

Send a message

Tell me about your use case and I'll get back to you shortly.

By submitting you agree to be contacted about DisputeIQ. No spam — ever. Powered by Formspree.

Open for Collaboration

Ready to transform your
dispute operations?

DisputeIQ is built by Ravi Appana — product builder and AI engineer focused on financial services automation. Available for demos, integrations, and consulting.

📧 Get in Touch Explore Architecture
🎯
Live Demo

Walk through a full dispute intake session — end to end in under 3 minutes.

🔌
API Integration

Drop the REST endpoints into your existing issuer portal or agent desktop.

🛠️
Custom Build

Need more reason codes, custom scoring, or workflow triggers? Let's scope it.