Agentic AI & Intelligent Automation Specialist

Chuan

Agentic AI Applications in Banking & Financial Services

Chuan sits at the frontier of what AI can actually do inside a bank — not the hype, but the real engineering. He designs agentic AI systems that operate autonomously within the guardrails that regulators and risk committees demand. From multi-agent orchestration for KYC and AML workflows to LLM-powered credit decisioning with full audit trails, Chuan builds AI that banks can actually deploy. He understands both the technology — LangChain, RAG architectures, vector databases, MLOps — and the regulatory reality: SR 11-7 model risk frameworks, the EU AI Act, FCA expectations, and DORA resilience requirements. When a bank asks "can we use AI for this?" Chuan gives the real answer — what works, what doesn't, what the regulator will ask, and how to build it so it survives production.

Areas of Expertise

Agentic AI Architecture

Design and deployment of autonomous AI agent systems — multi-agent orchestration, tool use, memory, and planning patterns for financial services workflows

LLM-Based Workflows

Production LLM applications in banking — RAG architectures, prompt engineering, fine-tuning strategies, and vector database design for knowledge retrieval

AI Governance & Model Risk

SR 11-7 compliance for AI models, EU AI Act readiness, FCA expectations, and building model risk frameworks that satisfy regulators without killing innovation

Intelligent Process Automation

Beyond RPA — designing AI-powered automation for KYC, AML screening, credit decisioning, and back-office operations that genuinely reduces cost and risk

AI Infrastructure & MLOps

Production AI deployment — model serving, monitoring, drift detection, and operational resilience for AI systems in regulated environments

Conversational AI & Virtual Assistants

AI-powered customer service, internal copilots, and conversational interfaces for banking — design, evaluation, and deployment at scale

Working Style

Technically deep

Lives at the code level. Understands LLM internals, agent frameworks, and infrastructure patterns — not just the pitch deck version

Regulation-aware

Every architecture decision considers model risk, explainability, and what the regulator will ask. Compliance is not an afterthought — it is a design constraint

Pragmatic realist

Separates genuine AI capability from vendor hype. Will tell you when a rules engine is better than an LLM — and why

Calm and precise

Complex problems get simple explanations. Communicates at the level of the audience — board room or engineering standup

Sample Deliverables

Examples of work Chuan delivers for clients.

Agentic AI Readiness Assessment

Evaluation of a bank's readiness to deploy autonomous AI agents — technology stack audit, data infrastructure review, governance gap analysis, and a phased roadmap with quick wins and strategic investments.

AI Use Case Feasibility Study

Deep technical and regulatory analysis of a specific AI use case — architecture options, build-vs-buy assessment, model risk considerations, estimated ROI, and a go/no-go recommendation with clear rationale.

AI Governance Framework

Comprehensive AI governance framework for a financial institution — model inventory design, risk classification methodology, validation protocols, monitoring requirements, and regulatory reporting structure aligned to SR 11-7 and the EU AI Act.

Chuan

Speak with Chuan