CXAiQ · Logistics & Express Parcel · Customer Operations, Deflection & Fraud

Fix the parcel before the phone rings.

CXAiQ pulls every scan, delivery attempt, customs hold, call, chat and driver handoff into one Neo4j knowledge graph — so an express carrier can deflect the contact before it happens, explain exactly why contacts spike, and intercept fraud the rule engines miss. One substrate, three pillars, every decision audited and reversible.

Grow● Deployed & running in the cloudSaaS · any cloud · your cloud
The problem

An express carrier runs on events the customer never sees.

Scans, sort decisions, customs holds, handover handshakes, route deviations — by the time a customer calls, the cost is already locked in, and the connections that explain it are scattered across a dozen authoritative-but-disconnected systems.

01
The cost is locked in before the callWISMO ("where is my order") calls are a large share of contact volume, but the carrier only learns a problem is cascading after the calls arrive — when intervention is too late and unmeasured cost is already incurred.
02
Customer Ops and Network Ops are siloedThe contact centre owns cost-per-call; the network owns the exceptions that cause those calls. Neither sees the "this customer called about this package scanned at this hub by this driver" chain, because it's never joined in one place.
03
Emerging themes surface too slowlyNew contact reasons and intents take 30+ days to surface in a hand-maintained taxonomy, so network-shaped problems persist long after they could have been fixed.
04
Over-triggering fraud rules damage CXIdentity rings, driver-customer collusion and route-damage anomalies are graph patterns. Relational rule engines miss them — and high false-positive rates turn enforcement into customer-experience damage.
How CXAiQ works

One loop, from operational event to proven contact-cost avoided.

The disciplined Amplinth loop, tuned to express logistics — events become a graph, the graph answers honestly, action stays bounded, and every outcome is attributed, not assumed.

01

Classify

LLM extraction maps every call, chat & email to an L1→L2→L3 intent taxonomy on the graph. No black box.

02

Score honestly

GDS — PageRank, Louvain, WCC, FastRP — and a calibrated, monitored call-probability model write scores back as node properties.

03

Act bounded

Proactive SMS/email through a consent → frequency → quiet-hours gate, with a one-click kill switch. Freezes are reversible.

04

Prove = EVA

An attribution loop earns the avoided-contact count; contact cost avoided becomes an EVA ledger line.

05

Audit

Every action is a citable record on an append-only log — usable in a partner-data audit, a complaint, or a post-mortem.

Capabilities

Fifteen use cases across five working buckets.

Three value pillars — Visibility, Deflection and Fraud — plus the composable ingestion that feeds them, all reading one graph that puts the customer and the parcel at the centre.

Visibility — why contacts spike, and root cause

Intent taxonomy (L1→L2→L3) and root-cause PageRank rank the most impactful preventable causes; Louvain intent communities, drift detection (volume / velocity / community shift), emerging-pattern surfacing, a Sankey interaction→intent→root-cause flow and a UMAP scatter make the cascade legible to Network Ops.

Deflection — predict the call, intervene first

A calibrated call-risk model ranks high-risk cohorts; node-similarity "digital lookalikes" find phone-preferring customers who behave like self-servers; durable customer segments persist across runs; proactive SMS & email notifications close the loop — with an attribution loop so the avoided-contact number is earned, not assumed.

Compliance & bounded action — kill switch + PII anonymisation

Every send passes a bounded-action eligibility gate: kill switch → live consent (never cached) → frequency cap → quiet hours, each suppression logged with a typed reason for cheap audit. A read-only Cypher validator guards the graph assistant, and an anonymisation discipline keeps raw text and PII out of the graph entirely.

Fraud — identity rings, collusion & GraphRAG

WCC identity rings expose customers sharing addresses and burner emails; reversible, audited account freezes act on them; driver-customer collusion (Louvain) and Isolation-Forest novel-typology scoring over FastRP embeddings surface schemes the rule engines miss; de-identified GraphRAG gives investigators the evidence subgraph, not just a score.

Ingestion — CSV to Kafka, one composable framework

A six-stage adapter pipeline (Connector → Parser → Validator → Mapper → Enricher → Emitter) lands canonical Avro events on Kafka under a versioned Schema Registry; CSV upload-and-apply, streaming graph loaders, a Visual Mapper and a medallion lakehouse mean a new source is a configuration exercise, not a rebuild.

The substrate — one graph, three pillars

Visibility, Deflection and Fraud aren't three products stitched together: they read the same Neo4j source of truth, share the same GDS machinery (the Louvain that clusters intents also detects collusion), and write scores back transactionally so reads never see a half-applied score. The marginal cost of the third pillar is low because the substrate is shared.

Outcomes

Operator-set twelve-month targets.

The figures below are the steady-state targets an express carrier sets at the outset — the basis for the EVA business case, not realized client results. CXAiQ is built to attribute progress against the carrier's own baseline, so each one becomes an earned, defensible number.

40%→20%
WISMO call share · target
Operator 12-month target
15%→50%
Proactive notification coverage · target
Operator 12-month target
+200%
Fraud-ring detection, same false-positive budget · target
Operator 12-month target
35%→<10%
Fraud false-positive rate · target
Operator 12-month target
Earned, not assumed
Emerging themes that take 30+ days to surface today — the target is under 7 days, with drift & emerging-pattern detection already built.
The platform is real today: nine packages, ~175 test files, full infrastructure-as-code, deployed and running in the cloud. Code existence proves a capability is built — it does not turn a target into a realized result, so every headline figure here stays labelled as a target until a baseline is set.

All headline outcome figures are operator-set targets from the value model, not realized client benchmarks. They become realized, attributed figures once a design-partner baseline is in place.

Deployment & trust

Connect → Reason → Act & Prove.

Connect the six-stage adapter framework to TMS/WMS/CRM (CDC), booking webhooks, MQTT telematics, partner SFTP/EDIFACT, M365 and Genesys transcripts. Reason over a Neo4j graph with a GDS registry running on cadence. Act through a bounded, reversible eligibility gate — and Prove every avoided contact on an append-only audit log that ties straight to EVA.

Anonymisation gatewayAppend-only auditRead-only Cypher assistantBounded-action kill switchHuman-in-the-loopOkta OIDC + MFA
SaaS
Amplinth SaaS on AWSFully managed — fastest path to value.
VPC
Your own cloud / VPCCustomer and parcel data never leave your control.
Any cloud / regionAzure, GCP, AWS — data residency by default.
Why Amplinth

Scored, audited, reversible.

Graph-native, not bolted on

The hardest questions — "which root causes are most impactful?", "which customers share identity?", "which drivers cluster suspiciously?" — are literally PageRank, WCC and Louvain. Solving them on a graph substrate is an order of magnitude less code than the relational equivalent, and dashboards can't claim it.

Governance in the data path

The graph never sees raw text. An anonymisation gateway, append-only audit as an invariant, a read-only-allowlist assistant, de-identified GraphRAG and a bounded-action eligibility gate with a kill switch make explainability concrete — every action citable, reviewable and reversible.

Honest, attributed value

A deflection attribution loop and a calibrated, monitored model mean the contact-avoidance number is earned — the basis for an EVA ledger rather than a vanity metric. We label every target as a target until a baseline makes it real.

See CXAiQ on your contact data

Stop the call before it happens.

Book a 30-minute demo on your hardest contact-volume problem — we'll walk the Visibility, Deflection and Fraud loop on the graph, and the EVA business case behind it.