About
I'm Dhanyathep Phankajornvech. Most people call me Phu. I'm a first-year student at Chulalongkorn University in Bangkok, and most of my time outside lectures goes into building software.
What I do
My interest in technology goes beyond writing code. I'm fascinated by how software systems work together, how businesses operate behind the scenes, and how artificial intelligence can make complicated processes more accessible.
I started with independent projects and experiments. Over time those grew into larger systems involving databases, AI models, web applications, infrastructure, and business workflows.
Some of my current work is about real business operations, such as running a Muay Thai school's services or making enterprise data easier to understand. Some of it is about the engineering itself: local AI infrastructure, agent orchestration, system monitoring, and interactive business simulation.
I'm early in this, and I'm building with a long view.
Why I build
Building, not only studying
I'm a university student, but much of what I learn comes from work outside the classroom: software meant for real businesses and real users, not exercises.
Starting from the business
Most of my projects begin with an operational problem. A school handling international customers and visa questions. A company that cannot easily question its own ERP. A wholesaler tracking stock and accounts.
Systems, not just websites
I think about the whole product: the experience, the backend, security, cost, deployment, and how it could eventually be sold.
Toward independent products
My ambition is to build products under my own brand that earn customers and recurring revenue. That is a direction, not yet a company.
How I work
I design the system, write the specification, and direct AI coding agents through implementation. I dispatch their work deliberately and keep them supervised. Architecture, test requirements, and release decisions stay with me. I say so plainly because that is how I actually work, and a portfolio should be honest about who did what.
AI engineering
The AI work here is application engineering and agent infrastructure: making models useful and safe inside real systems, not research.
Local inference
Running models on my own hardware with LM Studio and llama.cpp: model selection, memory limits, quantization, GGUF formats, and Metal acceleration.
Supervised agents
Agents with separate responsibilities, such as an engineering agent and a customer-service agent, dispatched deliberately rather than left to run unrestricted.
Tool integration
Connecting models to structured business data through narrow tools, with a hard line between what an agent can read and what it can change.
Infrastructure
Serving models locally, connecting inference to applications over APIs, and weighing cloud against local deployment.
Education
Chulalongkorn University
BISTECH, first year · 2026 to present
- Mathematics
- Engineering
- Computer science
- Artificial intelligence
- Technology entrepreneurship
Where this is going
I'm particularly interested in building independent software products that bridge modern technology and real business needs, with a focus on AI, automation, and scalable systems.
SaaS
Products a business subscribes to, rather than one-off builds.
Enterprise AI
AI that reaches existing operational systems through secure, narrow integrations.
Business automation
Replacing repetitive administration with structured digital workflows.
Developer infrastructure
Tools for managing agents, compute, and software projects.
Thailand-focused technology
Problems in the Thai market that software can actually solve.
The lab
I work across three machines, and I've been experimenting with linking them into one shared development environment. It is a personal setup, not a production cluster.
Mac Studio
Apple M5 Max, 36 GB unified memory
Development, local AI inference, and backend experiments
Windows PC
NVIDIA RTX 4070
GPU workloads, Windows development, and testing
MacBook
Apple M2
Portable development and remote access
- macOS
- Windows 11
- Ubuntu on WSL2
- Node.js
- pnpm
- PostgreSQL
- Docker
- Git
- Tailscale
Off the keyboard
Practical shooting
A background in competitive practical shooting, which shaped how I think about precision, discipline, and performance under pressure.
Brazilian Jiu-Jitsu
Training regularly. Currently a four-stripe blue belt.
Hardware and networking
Building machines, wiring up a home lab, and running models locally. Some gaming too.
Coffee
Taken seriously, usually while something compiles.
Languages
Thai · English · French (beginner)
Contact
Have a system worth building?
I'm interested in real business problems, especially where AI has to work with existing data and existing people.