SEAN HONG

AI & Automation Engineer

I architect intelligent automation workflows and conversational AI systems. By leveraging n8n, JavaScript, and advanced RAG architectures, I connect complex data pipelines and build solutions that eliminate manual workloads so teams can focus on high-impact work.

Test Automation Engine Get in Touch

n8nAutonomous Flows

RAGZero-Leakage AI

APILive Integrations

Sean Hong - Workflow Automation Engineer

n8n

JavaScript

LangChain

AWS

Azure

GitHub

Next.js

React

Node.js

Python

PostgreSQL

MongoDB

Supabase

Postman

Tailwind CSS

n8n

JavaScript

LangChain

AWS

Azure

GitHub

Next.js

React

Node.js

Python

PostgreSQL

MongoDB

Supabase

Postman

Tailwind CSS

n8n

JavaScript

LangChain

AWS

Azure

GitHub

Next.js

React

Node.js

Python

PostgreSQL

MongoDB

Supabase

Postman

Tailwind CSS

Live n8n Automation Engine

Wanna AutomateYour Daily Repeat RoutineorYour System?

Professionals waste countless hours every week on repetitive, manual tasks. That is time and energy that should be spent creating actual business value. By integrating the right APIs and custom workflow logic, your daily operational systems can run themselves.

n8nActive Workflow: Portfolio RAG Agent (TypeSafe Guardrails)

n8n + Pinecone + Gemini + Jev

Visual Execution GraphStatus: Live Pipeline

Chat TriggerWebhook / POST

Ingests user chat payload { chatInput } via HTTPS webhook, validates payload schema, and assigns a session UUID.

Idle

Jev System 1 GuardrailInbound Semantic Router

Classifies intent, scans for prompt-injection vectors, and verifies the query is within scope of Sean's professional experience.

Idle

Conditional BranchRouter / IF Switch

Evaluates inbound guardrail score: Routes valid portfolio queries to Pinecone RAG; deflects malicious probes or off-topic prompts.

Idle

RAG AI AgentPinecone + Gemini 1.5/2.5

Performs dense vector similarity search across Sean's indexed work history in Pinecone, combining retrieved chunks with Gemini for grounded generation.

Idle

Jev Sanitization LayerOutbound PII / Leak Gate

Scans candidate response for sensitive PII, internal system prompts, or hallucinated facts before authorizing delivery.

Idle

Response DispatchHTTP Response / 200 OK

Returns JSON payload { output: '...' } back to client with execution latency telemetry and status confirmation.

Idle

Inspecting: Chat TriggerStep 1 of 6

Ingests user chat payload { chatInput } via HTTPS webhook, validates payload schema, and assigns a session UUID.

Talk to Sean's AI

Live Agent

Grounded with Pinecone RAG & TypeSafe Jev

Hello! 👋 I'm Sean's portfolio AI assistant. I'm connected to a live n8n workflow backed by Pinecone vector search and Gemini, guarded by TypeSafe Jev.

Ask me anything about Sean's engineering background, tech stack, or automation projects!

Just now

Suggested Prompts:

>_ Test My Automation Engine — Live Execution StreamRuntime: Self-Hosted n8n + Pinecone Vector + Gemini

Every query triggers the full guardrailed pipeline. Track each node's status above while reviewing execution milestones below in real-time.

>System ready. Enter a query in the chat to trigger the live n8n pipeline.

Enterprise AI & RAG Solutions

Lets talk about AI...

Traditional LLMs are built for general usage. They do not know your internal operations, your customer history, or your proprietary data and they do not know what information is strictly confidential.

Enterprise RAG AI WhatsApp Chatbot Assistant

Pillar 01

The RAG Advantage

I build Retrieval-Augmented Generation frameworks that connect powerful AI models directly to your private databases and company documents.

Pillar 02

Secure & Specific

Whether it is an internal knowledge base or a customer-facing support bot, the AI only references your approved data, ensuring every response is accurate, safe, and highly relevant to your business.

Track Record & Credentials

Experience & Education

Proven track record of architecting real-world autonomous workflows, high-throughput WhatsApp bots, and vector RAG systems for enterprise deployments.

Internship / Production System

TBUN Institute of Technology

AI Engineer (Intern)

Engineered a production-grade WhatsApp automation system using n8n and JavaScript to manage webinar registrations and intelligent absentee follow-ups.

n8n WorkflowsJavaScriptWhatsApp Cloud APIData PipelinesAbsentee Triggers

Full-stack / IoT & AI Automation

HAVVA Agrotech

Smart Automation Engineer

Created an automated scheduling pipeline via an OpenAI-powered n8n agent and built custom IoT monitoring infrastructure.

OpenAI APIn8n AgentsIoT SensorsAutomated SchedulingPython / Node.js

Internship / RAG & Cloud Migration

HAVVA Agrotech

Software Developer (Intern)

Spearheaded the R&D of a RAG WhatsApp chatbot and led its enterprise migration to Microsoft Azure using GPT-4o and MongoDB vector databases.

RAG ArchitectureGPT-4oMicrosoft AzureMongoDB Vector StoreWhatsApp Bot

Academic Qualifications

Jan 2026 – Present

Bachelor in Software Engineering

Wawasan Open University

Penang, Malaysia

Application Development

May 2023 – Sep 2025

Diploma in Information Technology

UOW Malaysia

Penang, Malaysia

Certification

HRDF Certified

Feb 2025

Professional AI Engineering

Skills:Prompt EngineeringRetrieval Augmented Generation (RAG)Fine-Tuning

Let’s Build Together

Contact Me

Ready to reclaim your time and scale your systems? Let’s connect.

SEAN HONG

Open to Contracts

Specialized in architecting n8n workflows, custom API connectors, and confidential RAG chatbots.

Average response time: < 24hPenang, Malaysia (GMT+8)

Send an Inquiry

Tell me about your business challenge, desired n8n flow, or AI RAG integration.

Dispatched securely via n8n automation pipelineAll communications strictly confidential