AI-READY ENTERPRISE ARCHITECTURE

Fisher Investments

Transforming Wealth Management Through Intelligent Automation

Executive Summary

Fisher Investments' Enterprise AI Architecture represents a comprehensive, battle-tested solution built on open source components and Azure cloud infrastructure. Managing $362 billion in assets under management (AUM) across 174,538 client accounts, this architecture seamlessly integrates data from Salesforce Financial Services Cloud, Bloomberg Terminal, ServiceNow, Workday, and proprietary knowledge systems to power intelligent decision-making across the organization.

The platform leverages NVIDIA-accelerated AI/ML orchestration with cutting-edge capabilities including model serving (NVIDIA Blueprints, Model Registry), agent frameworks (AgentBlocks, Langgraph, MCP, A2A), real-time ML (NVIDIA Triton, KServe), large language model services (NVIDIA NIM, Llama Family, NVIDIA Nemotron), text-to-SQL generation (Databricks Genies, Databricks Deep Insights), MLOps (MLflow, Experiments, Model Versioning), vector search (Milvus GPU, NVIDIA CuVS), and feature stores (Feast, Drift Monitoring).

Built on a robust Databricks-powered data platform with Delta Lake architecture, the system processes real-time market data, client interactions, and operational metrics through a unified semantic layer powered by dbt and Databricks Unity Catalog. Azure Purview ensures comprehensive data governance with automated PII detection, lineage tracking across extensive datasets, and SEC/FINRA-ready audit reports.

The architecture delivers measurable business impact: the AI Agent Assist system handles significant annual inquiries with high resolution rates, Kitchen Sink application processes high weekly lead query volumes with conversion improvement, and AI-Powered Targeting achieves higher engagement through intelligent customer segmentation. The Fisher KI (Knowledge Intelligence) system serves as a centralized repository of investment philosophy and operational excellence. Security and compliance are paramount, with SOC 2 Type II certification, multi-factor authentication across all 6,300 employees, end-to-end encryption (AES-256 at rest, TLS 1.3 in transit), and high uptime SLA with robust disaster recovery.

Application Layer - AI-Powered Business Solutions

Production AI applications delivering measurable business outcomes: AI Agent Assist resolving significant inquiries annually with high success rates, Kitchen Sink processing high weekly lead query volumes driving conversion improvement, AI-Powered Targeting and Customer Segmentation achieving higher engagement through intelligent personalization, and Fisher KI serving as the centralized knowledge intelligence hub. Each application leverages the full AI/ML orchestration stack with real-time model serving, agent frameworks, and vector search capabilities.

AI Agent Assist

Intelligent Client Service Automation

AI-powered assistant handling significant annual client inquiry volumes across phone, email, and chat channels. Leverages NVIDIA NIM and Llama models with real-time context from Salesforce FSC, reducing average handling time significantly.

  • High resolution rate without human escalation
  • Real-time account access: portfolio performance, transaction history, tax documents
  • Context-aware responses: retrieves Ken Fisher philosophy, market commentary
  • Multi-channel deployment: phone IVR, web chat, email triage
  • Compliance guardrails: SEC-approved responses with audit trails

Kitchen Sink

Lead Qualification & Conversion Engine

Processes high weekly lead inquiry volumes through intelligent scoring and routing. Uses Databricks Genies for text-to-SQL querying across lead database, Bloomberg market data, and Salesforce opportunity pipeline.

  • Conversion improvement through predictive lead scoring
  • Automated lead enrichment: net worth estimation, investment profile
  • Smart routing: matches leads to best-fit advisors based on specialty
  • Real-time market triggers: alerts advisors when lead-relevant news breaks
  • Salesforce FSC integration: seamless handoff with full context

AI-Powered Targeting and Customer Segmentation

Intelligent Marketing & Personalization

Advanced segmentation engine using Milvus vector search and NVIDIA CuVS to identify micro-segments across 174,538 clients. Drives personalized content, outreach timing, and product recommendations.

  • Higher engagement vs. rules-based segmentation
  • Behavioral clustering: groups clients by investment style, risk tolerance
  • Event-triggered campaigns: retirement, inheritance, market volatility
  • Next-best-action recommendations: upsell opportunities, retention alerts
  • Drift monitoring: Feast feature store tracks segment stability

Fisher KI

Knowledge Intelligence Repository

Centralized AI-powered knowledge system indexing Ken Fisher's books, investment philosophy, policy documents, and operational procedures. Powered by vector search (Milvus GPU) and retrieval-augmented generation (RAG) with NVIDIA NIM.

  • Instant access to decades of Fisher investment wisdom
  • Semantic search: finds relevant content beyond keyword matching
  • Advisor onboarding: significantly faster ramp time for new hires
  • Compliance Q&A: policy lookups with source citations
  • Conversational interface: natural language queries across all documents

AI/ML Orchestration Layer - NVIDIA-Powered Intelligence

Enterprise-grade AI/ML infrastructure powered by NVIDIA GPUs (A100/H100) with comprehensive orchestration capabilities. Model serving through NVIDIA Blueprints and Model Registry, agent frameworks (AgentBlocks, Langgraph, MCP, A2A), real-time ML inference (NVIDIA Triton, KServe), LLM services (NVIDIA NIM, Llama Family, NVIDIA Nemotron), intelligent querying (Databricks Genies, Databricks Deep Insights), MLOps (MLflow, Experiments, Model Versioning, Performance Monitoring), vector search (Milvus GPU, NVIDIA CuVS, GPU Acceleration), and feature engineering (Feast, Drift Monitoring).

Model Serving

  • NVIDIA Blueprints
  • Model Registry
  • A/B Testing
  • Canary Deployment

Enterprise Model Deployment

NVIDIA Blueprints provide pre-built AI workflows for financial services, while the Model Registry tracks versions, performance metrics, and deployment history across production models.

Deployment Features:

• NVIDIA Blueprints: pre-optimized AI workflows
• Model Registry: version control, lineage tracking
• A/B Testing: champion/challenger comparison
• Canary Deployment: gradual rollouts with monitoring
• Auto-scaling: dynamic resource allocation

Agent Framework

  • AgentBlocks
  • Langgraph
  • MCP
  • A2A

Multi-Agent Orchestration

AgentBlocks and Langgraph enable complex multi-agent workflows for AI Agent Assist and Kitchen Sink. MCP (Model Context Protocol) ensures consistent context sharing, while A2A (Agent-to-Agent) enables autonomous collaboration.

Framework Capabilities:

• AgentBlocks: modular agent components
• Langgraph: visual agent workflow design
• MCP: shared context across agent interactions
• A2A: autonomous agent-to-agent communication
• Tool integration: Salesforce, Bloomberg APIs

Realtime ML

  • NVIDIA Triton
  • KServe
  • Online Inference
  • NVIDIA vLLM (Open-source)

Low-Latency Model Inference

NVIDIA Triton Inference Server and KServe deliver low-latency model predictions for real-time applications. NVIDIA vLLM accelerates LLM inference for conversational AI with optimized GPU utilization.

Performance Specs:

• Triton: high-throughput predictions across A100 cluster
• KServe: Kubernetes-native serving with auto-scaling
• vLLM: significantly faster LLM inference vs. standard deployment
• Model ensembles: combine multiple models per request
• GPU sharing: multi-model deployment per GPU

LLM Services

  • NVIDIA NIM
  • Llama Family
  • NVIDIA Nemotron
  • Fine-tuned Models

Large Language Model Infrastructure

NVIDIA NIM (NVIDIA Inference Microservices) provides optimized LLM deployment, while Llama models power conversational AI. NVIDIA Nemotron delivers financial domain expertise with fine-tuned models on Fisher data.

LLM Stack:

• NVIDIA NIM: containerized LLM deployment
• Llama 3.3 70B: primary conversational model
• Nemotron: financial domain specialization
• Fine-tuning: Fisher-specific vocabulary, tone
• Safety guardrails: content filtering, compliance checks

Text-to-SQL

  • Databricks Genies
  • Databricks Deep Insights

Natural Language Data Querying

Databricks Genies converts natural language questions into optimized SQL queries, enabling business users to access data without technical expertise. Deep Insights provides automated analysis and recommendations.

Query Capabilities:

• Natural language interface: "show me top advisors by AUM"
• Context-aware SQL: understands table relationships
• Deep Insights: automated trend detection, anomalies
• Query optimization: efficient execution plans
• Audit trail: tracks all user queries for compliance

MLOps

  • MLflow
  • Experiments
  • Model Versioning
  • Performance Monitoring

ML Lifecycle Management

MLflow orchestrates the complete ML lifecycle from experimentation to production deployment. Tracks extensive experiments with automated versioning, performance monitoring, and model governance.

MLOps Features:

• Experiment tracking: hyperparameters, metrics, artifacts
• Model registry: centralized version control
• Performance monitoring: accuracy, latency, drift detection
• Automated retraining: triggers based on performance thresholds
• Reproducibility: containerized environments per model

Vector Search

  • Milvus (GPU)
  • NVIDIA CuVS
  • GPU Acceleration

High-Performance Similarity Search

Milvus GPU-accelerated vector database powers semantic search across Fisher KI documents, client profiles, and market research. NVIDIA CuVS provides optimized similarity algorithms for A100/H100 GPUs.

Search Performance:

• Millions of vectors indexed: documents, clients, securities
• Low query latency with GPU acceleration
• NVIDIA CuVS: optimized HNSW, IVF algorithms
• Hybrid search: combines semantic + keyword matching
• Real-time indexing: new content searchable within 1 min

Feature Store

  • Feast
  • Drift Monitoring

Centralized Feature Management

Feast feature store provides consistent feature definitions across training and inference. Drift monitoring detects distribution changes that degrade model performance, triggering automated retraining.

Feature Engineering:

• 500+ features: client demographics, portfolio metrics, behavior
• Real-time serving: low-latency feature retrieval
• Point-in-time correctness: prevents data leakage
• Drift detection: statistical tests on feature distributions
• Feature lineage: tracks transformations from raw data

Data Platform Layer - Unified Data Foundation

Enterprise data lakehouse built on Databricks with Delta Lake architecture, processing petabytes of structured and unstructured data. Ingestion through Event Hubs, Azure Data Factory, Debezium for real-time CDC. Storage layer spans Azure Data Lake, Azure SQL, Azure Cosmos DB. Data governance powered by Azure Purview with automated PII detection and lineage tracking across extensive datasets. Processing powered by Kafka, Databricks, Delta Lake, Apache Spark. Semantic layer built on dbt, Databricks Unity Catalog, Metrics Store, Business Logic ensuring single-source-of-truth definitions.

Data Ingestion

  • Event Hubs
  • Azure Data Factory
  • Debezium

Real-Time & Batch Data Ingestion

Azure Event Hubs streams high-volume events daily from Bloomberg, Salesforce, ServiceNow. Azure Data Factory orchestrates extensive batch pipelines. Debezium captures database changes from Workday, legacy systems.

Ingestion Specs:

• Event Hubs: high daily message volume, low latency
• ADF: extensive pipelines, substantial data processed daily
• Debezium: CDC from Oracle, SQL Server, PostgreSQL
• Schema validation: ensures data quality at ingestion
• Dead letter queues: failed messages for retry

Data Storage

  • Azure Data Lake
  • Azure SQL
  • Azure Cosmos DB

Multi-Tiered Storage Architecture

Azure Data Lake stores raw, bronze, silver, and gold data tiers (10+ PB). Azure SQL for structured reporting databases. Cosmos DB for low-latency, globally distributed application data.

Storage Layers:

• Data Lake: 10+ PB across hot, cool, archive tiers
• Azure SQL: multiple databases for reporting, analytics
• Cosmos DB: low read latency for apps
• Lifecycle policies: auto-tier data based on age
• Geo-replication: RA-GRS for disaster recovery

Data Governance

  • Azure Purview
  • Data Catalog
  • Lineage Tracking
  • RBAC

Enterprise Data Governance

Azure Purview provides unified data governance, discovery, and compliance management across Fisher's entire data estate with automated PII detection.

Compliance Features:

• Data catalog: extensive datasets searchable
• Lineage: trace data from source to dashboard
• Sensitivity labels: auto-detect SSN, financial data
• Access analytics: who accessed what, when
• SEC/FINRA audit-ready reports

Data Processing

  • Kafka
  • Databricks
  • Delta Lake
  • Apache Spark

Scalable Data Processing

Kafka event streaming with high daily message volumes. Databricks Lakehouse processes substantial data daily with Delta Lake ACID transactions. Spark jobs transform raw data into analytics-ready gold tables.

Processing Capabilities:

• Kafka: high daily event volume, topic partitioning
• Databricks: extensive Spark clusters, auto-scaling
• Delta Lake: ACID, time travel, schema evolution
• Spark: batch + streaming, high daily throughput
• Medallion architecture: bronze, silver, gold layers

Semantic Layer & Metrics Store

dbt + Databricks Unity Catalog - Unified business metrics ensuring consistency across all AI applications and analytics. Features include Client 360 Views, Advisor Performance Dashboards, and Regulatory Reporting with single-source-of-truth definitions.

Infrastructure & Security Layer

Battle-tested Azure foundation with multi-region deployment delivering high uptime. NVIDIA A100/H100 GPU clusters powering extensive AKS nodes for AI workloads. Defense-in-depth security: Azure AD + MFA for all 6,300 employees, Key Vault for secrets management, AES-256 at Rest / TLS 1.3 in Transit encryption, SOC 2 Type II compliance. Networking via Virtual Network, Private Link, ExpressRoute (high bandwidth), Azure Firewall, DDoS Protection. Comprehensive observability through Azure Monitor, Application Insights, Log Analytics, OpenTelemetry. Robust disaster recovery capabilities.

Cloud Platform

  • Microsoft Azure
  • Azure DevOps
  • Container Registry
  • NVIDIA

Azure Cloud Foundation

Fisher's cloud-native infrastructure built on Microsoft Azure provides enterprise-grade compute, storage, and networking with multi-region deployment for high availability. NVIDIA GPU infrastructure powers AI/ML workloads.

Infrastructure Specs:

• Primary: East US 2 (near Plano, TX HQ)
• Secondary: West US 2 (DR site)
• AKS: extensive nodes for AI workloads
• NVIDIA A100/H100 GPU pools
• High uptime SLA with auto-scaling

Security

  • Key Vault
  • Azure AD + MFA
  • AES-256 at Rest
  • TLS 1.3 in Transit
  • SOC 2 Type II

Defense-in-Depth Security

Multi-layered security architecture ensuring data protection, access control, and compliance with financial services regulations (SEC, FINRA, SOC 2).

Security Controls:

• Azure AD: SSO + MFA for all 6,300 employees
• Key Vault: secrets, API keys, certificates
• RBAC: least-privilege access
• Encryption: AES-256 at rest, TLS 1.3 in transit
• Annual SOC 2 Type II audits

Networking

  • Virtual Network
  • Private Link
  • ExpressRoute
  • Azure Firewall
  • DDoS Protection

Secure Network Architecture

Private networking with ExpressRoute dedicated connections from Fisher offices to Azure, ensuring low-latency and secure data transmission.

Network Features:

• VNet isolation: application, data, gateway subnets
• Private Link: Azure services never on public internet
• ExpressRoute: high-bandwidth dedicated connection
• Azure Firewall: application-aware filtering
• DDoS Standard: automatic attack mitigation

Observability

  • Azure Monitor
  • Application Insights
  • Log Analytics
  • OpenTelemetry

Full-Stack Observability

Comprehensive monitoring and alerting across infrastructure, applications, and ML models with distributed tracing for debugging complex AI workflows.

Monitoring Capabilities:

• Azure Monitor: metrics, logs, alerts
• Application Insights: APM for AI apps
• Log Analytics: centralized log aggregation
• OpenTelemetry: distributed tracing end-to-end
• Custom dashboards: real-time KPIs

Source Systems Layer - Enterprise Applications

Unified integration across Fisher's enterprise ecosystem: Salesforce FSC managing $362B in AUM, Workday powering global HR operations, Bloomberg Terminal delivering real-time market intelligence, ServiceNow orchestrating significant annual ticket volumes, and comprehensive knowledge repositories including Ken Fisher's investment philosophy and policy documents. Seamless data federation powering intelligent decision-making across the organization.
UNSTRUCTURED DATA

Ken Fisher Books
Policy Documents
SharePoint Docs

SALESFORCE FSC

Client CRM
174,538 Accounts
Activity Tracking

SERVICENOW

IT Service Mgmt
Significant Annual Tickets
Change Tracking

BLOOMBERG

Market Data
Research Reports
Live News Feeds

WORKDAY

HR Management
6,300 Employees
Org Hierarchy

Enterprise AI Architecture Solutions