Redis Real-Time Decisioning Demo | Call Center Next Best Action

Stage 1: The Architecture

Vertex Wireless's Real-Time Decisioning Stack

Five tiers form a continuous loop: ingest, context, decide, act, learn. Same expert. Same call. One decision layer turns a generic save offer into a context-aware recovery plan. Systems of record stay where they are. Redis becomes the operational context layer that makes the moment actionable.

Data Sources

CRM / Billing Platform

Operational source

Interaction History Store

Operational source

Network Telemetry APIs

Operational source

Offer Catalog

Operational source

Databricks Feature Pipeline

Operational source

Kafka / Contact Center Events

Operational source

Ingest Layer

Redis Data Integration (RDI)

CDC from repositories and operational databases with sub-second activation

Redis Feature Form + Streams

Feature serving and live event hydration from Kafka, Redis Streams, and industry APIs

Unified Context Layer

Redis RAM

Hot interaction state, live sentiment signals, active case flags, and current channel context

Redis Flex

Warm interaction history, issue resolution embeddings, customer lifetime context, and prior NBA outcomes

Feature Store

Churn risk, NPS propensity, offer eligibility, and escalation likelihood features

Redis Context Retriever

Assembles the Member 360 — account state, interaction history, and product context — and exposes it as structured MCP tools for the decision engine

Decision Engine

Eligibility Rules

Policy, compliance, and inventory constraints

NBA Ranker

Contextual ranking weighted by value, risk, and fit

Policy Arbitration

One action selected for the current moment

Output Channels (Act)

Agent Desktop

Customer-facing activation surface

Mobile App

Customer-facing activation surface

Web Account Center

Customer-facing activation surface

SMS / Email

Customer-facing activation surface

↺

Learn: Decision logs and outcomes stream back into model training, policy updates, and the Redis context layer.

Decision latency

8.2 ms

Save-rate lift

+23 pts

Incremental household LTV

+$3,480

Stage 2: Trigger Event

Maya Johnson creates a decision moment

A high-value subscriber calls support after repeated service issues and a recent billing complaint. Resolve the issue first, then convert the moment into a retention and expansion event.

Live Trigger

Maya Johnson

4 lines | 8-year customer | household ARPU $212 | premium plan

CARE

Eventsupport_session_start

Customer surfaceAgent desktop

Decision objectiveRetention + upsell

Decision windowBefore the surface finishes rendering

Context requiredHistory + live signals + policy

Business stakes+23 pts

Why This Moment Matters

Same expert. Same call. One decision layer turns a generic save offer into a context-aware recovery plan.

Without Redis: the application waits on siloed repositories and defaults to a generic next step.

With Redis: the decision surface opens with ranked, contextual action already staged for the moment.

Stage 3: Ingest

Industry repositories and streams flow into Redis

These are common repositories and streaming APIs for customer care decisioning. They remain the systems of record. Redis activates the working set needed to decide now.

Redis Data Integration (RDI)Redis Feature Form

Source Systems → Redis

SALE

Salesforce Service Cloud

Common repository or streaming source for salesforce context

→

SNOW

Snowflake / Databricks

Common repository or streaming source for snowflake context

→

KAFK

Kafka / Redis Streams

Event streaming via Kafka or Redis Streams — no separate broker required with Redis Streams built-in

→

TWIL

Twilio / IVR events

Common repository or streaming source for twilio context

→

COVE

Coverage diagnostics API

Common repository or streaming source for coverage context

→

Ingest Pipeline Status

CDC modeReal-time

Streaming lag<100 ms

Feature parityTrain = serve

Custom sync code0 lines

Serving roleOperational context layer

Stage 4: Context Assembly

History and live state converge into one working view

Redis assembles profile history, account or household state, live intent, and policy constraints in one low-latency lookup path. What looked like a simple event in Stage 2 becomes a much richer decision moment here.

Redis RAMRedis FlexRedis Context Retriever

Historical Context

Customer value bandtop decile

Tenure / relationship depthEstablished

Prior interaction patternKnown baseline available

Eligibility stateResolved in memory

Policy constraintsCurrent and active

Action historyFrequency caps enforced

Live Context

Current intentRetention + upsell

Streaming signal stateFresh for this session

Capacity / inventoryAvailable

Risk / complianceWithin active rules

Surface readinessAgent desktop

Decision scopeCoverage fix bundle + loyalty save

Key insight: Redis Context Retriever assembles the Member 360 — account state, interaction history, and product context — so the decision engine has exactly what it needs. The winning action becomes obvious only when historical context and live signals appear in the same response path.

Stage 5: Feature Serving

Online features hydrate the ranker in milliseconds

Redis Feature Form serves model-ready signals from Redis with train-serve parity. No fan-out calls to downstream systems during decisioning. No stale fallbacks.

Redis Feature FormRedis Feature Store

churn_risk_30d

Risk and policy factor used to gate the action.

0.740.3 ms

network_quality_index

Real-time feature served from Redis with train-serve parity.

0.310.4 ms

offer_acceptance_propensity

Model or ranking signal pulled online at decision time.

0.890.5 ms

tenure_ltv_score

Model or ranking signal pulled online at decision time.

top decile0.6 ms

home_internet_eligibility

Eligibility and readiness signal.

true0.7 ms

service_case_sentiment

Real-time feature served from Redis with train-serve parity.

negative0.8 ms

Feature Serving Performance

Features Hydrated

186

P99 Lookup Latency

<10ms

Train / Serve Parity

100%

Stage 6: Ranking

Candidate actions are ranked for this moment

Rules, policies, vector similarity, and business weighting combine to rank the best action now. The winner is selected because it fits the moment, not because it is the easiest generic fallback.

Redis SearchNBA RankerRules Engine

#1 Winner

PRIMARY ACTION

Coverage fix bundle + loyalty save

Free signal booster + home internet save plan

NBA score0.94

#2 Candidate

ALTERNATIVE

One-time service credit

Fast but generic and margin-negative

NBA score0.79

Suppressed

POLICY

Device upgrade promo

Strong fit later, but not while the service issue is unresolved

Suppressed0.24

Stage 7: Business Impact

The value of choosing the right action now

Fast decisions matter, but the real value is choosing the right action while the moment is still open. Redis improves both latency and outcome quality.

Decision Economics

Decision latency8.2 ms

Save-rate lift+23 pts

Incremental household LTV+$3,480

The key insight: value compounds when the decision surface uses live operational context instead of generic fallback logic.

Moment Outcome

Generic

Siloed systems
lower relevance

→

Redis

Context-aware
higher impact

Stage 8: Outcome

Same surface. Different decision layer.

On the left is a generic or delayed path. On the right is the Redis-powered experience with ranked action already staged. Same customer moment. Different outcome.

Generic Experience

Maya Johnson

Customer Care workflow

What the system knows

Partial profile, delayed retrieval, and limited live context.

Action shown

One-time service credit

Outcome risk

The action fits broadly, but not the full moment.

Lower

relevance

Higher

fallback use

Siloed

context

Redis-Powered Experience

Maya Johnson

Decision-ready profile

#1 Next Best Action

Coverage fix bundle + loyalty save

Free signal booster + home internet save plan

Why it wins

Combines history, live signals, business value, and active policy constraints in the same low-latency response.

Visible impact

Save-rate lift: +23 pts.

High

relevance

Low

fallback use

Ready

before render

Stage 9: The Architecture, Proven

Architecture first. Architecture last. Outcome in the middle.

The same five tiers you saw at the start now tie directly to a measurable decision outcome. Common repositories and streaming APIs stay in place. Redis remains the operational decisioning layer that makes the customer moment work.

Data Sources

CRM / Billing Platform

Operational source

Interaction History Store

Operational source

Network Telemetry APIs

Operational source

Offer Catalog

Operational source

Databricks Feature Pipeline

Operational source

Kafka / Contact Center Events

Operational source

Ingest Layer

RDI

CDC and activation from systems of record

Streams + Features

Live event hydration and model parity

Unified Context Layer

Redis RAM

Hot interaction state, live sentiment signals, active case flags, and current channel context

Redis Flex

Warm interaction history, issue resolution embeddings, customer lifetime context, and prior NBA outcomes

Feature Store

Churn risk, NPS propensity, offer eligibility, and escalation likelihood features

Redis Context Retriever

Assembles the Member 360 — account state, interaction history, and product context — and exposes it as structured MCP tools for the decision engine

Decision Engine

Rules

Eligibility, compliance, and policy

Ranker

Propensity, value, and fit

Arbitration

One action selected now

Output Channels

Agent Desktop

Customer-facing activation surface

Mobile App

Customer-facing activation surface

Web Account Center

Customer-facing activation surface

SMS / Email

Customer-facing activation surface

↺

Learn: Outcomes feed retraining, policy updates, and future decisions without changing the systems of record.

Decision latency

8.2 ms

Save-rate lift

+23 pts

Incremental household LTV

+$3,480